learning

Learning Philosophy:

• Data Scientists Should Be More End-to-End
• Just in Time Learning
• Master Adjacent Disciplines
• T-shaped skills
• The Power of Tiny Gains

Have basic business understanding

• Book: Delivering Happiness
• Book: Good to Great: Why Some Companies Make the Leap...And Others Don't
• Book: Hello, Startup: A Programmer's Guide to Building Products, Technologies, and Teams
• Book: How Google Works
• Book: Learn to Earn: A Beginner's Guide to the Basics of Investing and Business
• Book: Rework
• Book: The Airbnb Story
• Book: The Personal MBA
• Facebook: Digital marketing: get started
• Facebook: Digital marketing: go further
• Google Analytics for Beginners
• Moz: The Beginner's Guide to SEO
• Smartly: Marketing Fundamentals
• Treehouse: SEO Basics
• Udacity: App Monetization
• Udacity: App Marketing
• Udacity: How to Build a Startup

Be familiar with how ML is applied at other companies

• Article: How Facebook uses super-efficient AI models to detect hate speech
• Article: Recent Advances in Google Translate
• Article: Cannes: How ML saves us $1.7M a year on document previews
• Article: Machine Learning @ Monzo in 2020
• Article: How image search works at Dropbox
• Real-world AI Case Studies
  • Andrej Karpathy on AI at Tesla (Full Stack Deep Learning - August 2018)
  • Jai Ranganathan at Data Science at Uber (Full Stack Deep Learning - August 2018)
  • John Apostolopoulos of Cisco discusses "Machine Learning in Networking" 0:48:44
  • Joaquin Candela, Director of Applied Machine Learning, Facebook in conversation with Esteban Arcaute 0:52:27
  • Eric Colson, Chief Algorithms Officer, Stitch Fix 0:53:57
  • Claudia Perlich, Advisor to Dstillery and Adjunct Professor NYU Stern School of Business 0:51:59
  • Jeff Dean, Google Senior Fellow and SVP Google AI - Deep Learning to Solve Challenging Problems 0:58:45
  • James Parr, Director of Frontier Development Lab (NASA), FDL Europe & CEO, Trillium Technologies 0:55:46
  • Daphne Koller, Founder & CEO of Insitro - In Conversation with Carlos Bustamante 0:49:29
  • Eric Horvitz, Microsoft Research - AI in the Open World: Advances, Aspirations, and Rough Edges 0:56:11
  • Tony Jebara, Netflix - Machine Learning for Recommendation and Personalization 0:55:20
• Datacamp: Analyzing Police Activity with pandas
• Datacamp: HR Analytics in Python: Predicting Employee Churn
• Datacamp: Predicting Customer Churn in Python
• Youtube: How does YouTube recommend videos? - AI EXPLAINED! 0:33:53
• Youtube: How does Google Translate's AI work? 0:15:02
• Youtube: Data Science in Finance 0:17:52
• Youtube: The Age of AI
  • How Far is Too Far? | The Age of A.I. 0:34:39
  • Healed through A.I. | The Age of A.I. 0:39:55
  • Using A.I. to build a better human | The Age of A.I. 0:44:27
  • Love, art and stories: decoded | The Age of A.I. 0:38:57
  • The 'Space Architects' of Mars | The Age of A.I. 0:30:10
  • Will a robot take my job? | The Age of A.I. 0:36:14
  • Saving the world one algorithm at a time | The Age of A.I. 0:46:37
  • How A.I. is searching for Aliens | The Age of A.I. 0:36:12
• Youtube: Using Intent Data to Optimize the Self-Solve Experience
• Youtube: Trillions of Questions, No Easy Answers: A (home) movie about how Google Search works
• Youtube: Google Machine Learning System Design Mock Interview
• Youtube: Netflix Machine Learning Mock Interview: Type-ahead Search
• Youtube: Machine Learning design: Search engine for Q&A
• Youtube: Engineering Systems for Real-Time Predictions @DoorDash
• Youtube: How Gmail Uses Iterative Design, Machine Learning and AI to Create More Assistive Features
• Youtube: Wayfair Data Science Explains It All: Human-in-the-loop Systems
• Youtube: Leaving the lab: Building NLP applications that real people can use
• Youtube: Machine Learning at Uber (Natural Language Processing Use Cases)
• Youtube: Google Wave: Natural Language Processing
• Youtube: Natural Language Understanding in Alexa
• Youtube: The Machine Learning Behind Alexa’s AI Systems
• Youtube: Ines Montani Keynote - Applied NLP Thinking
• Youtube: Lecture 9: Lukas Biewald
• Youtube: Lecture 13: Research Directions
• Youtube: Lecture 14: Jeremy Howard
• Youtube: Lecture 15: Richard Socher
• Youtube: Machine learning across industries with Vicki Boykis 0:34:02
• Youtube: Rachael Tatman - Conversational A.I. and Linguistics 0:36:51
• Youtube: Nicolas Koumchatzky - Machine Learning in Production for Self Driving Cars 0:44:56
• Youtube: Brandon Rohrer - Machine Learning in Production for Robots 0:34:31
• Youtube: [CVPR'21 WAD] Keynote - Andrej Karpathy, Tesla

Be able to frame an ML problem

• AWS: Types of Machine Learning Solutions
• Article: Apply Machine Learning to your Business
• Article: Resilience and Vibrancy: The 2020 Data & AI Landscape
• Article: Software 2.0
• Article: Highlights from ICML 2020
• Article: A Peek at Trends in Machine Learning
• Article: How to deliver on Machine Learning projects
• Article: Data Science as a Product
• Article: Customer service is full of machine learning problems
• Article: Choosing Problems in Data Science and Machine Learning
• Article: Why finance is deploying natural language processing
• Article: The Last 5 Years In Deep Learning
• Article: Always start with a stupid model, no exceptions.
• Article: Most impactful AI trends of 2018: the rise of ML Engineering
• Article: Building machine learning products: a problem well-defined is a problem half-solved.
• Article: Simple considerations for simple people building fancy neural networks
• Article: Maximizing Business Impact with Machine Learning
• Book: AI Superpowers: China, Silicon Valley, and the New World Order
• Book: A Human's Guide to Machine Intelligence
• Book: The Future Computed
• Book: Machine Learning Yearning by Andrew Ng
• Book: Prediction Machines: The Simple Economics of Artificial Intelligence
• Book: Building Machine Learning Powered Applications: Going from Idea to Product
• Coursera: AI For Everyone
• Datacamp: Data Science for Everyone
• Datacamp: Machine Learning with the Experts: School Budgets
• Datacamp: Machine Learning for Everyone
• Datacamp: Data Science for Managers
• Facebook: Field Guide to Machine Learning
• Google: Introduction to Machine Learning Problem Framing
• Pluralsight: How to Think About Machine Learning Algorithms
• State of AI Report 2020
• Youtube: Vincent Warmerdam: The profession of solving (the wrong problem) | PyData Amsterdam 2019
• Youtube: Hugging Face, Transformers | NLP Research and Open Source | Interview with Julien Chaumond
• Youtube: Vincent Warmerdam - Playing by the Rules-Based-Systems | PyData Eindhoven 2020
• Youtube: Building intuitions before building models
• Youtube: Recent Breakthroughs in AI with Andrej Karpathy and Lex Fridman

Be familiar with data ethics

• Article: How to Detect Bias in AI
• Netflix: Coded Bias
• Netflix: The Great Hack
• Netflix: The Social Dilemma
• Practical Data Ethics
  • Lesson 1: Disinformation
  • Lesson 2: Bias & Fairness
  • Lesson 3: Ethical Foundations & Practical Tools
  • Lesson 4: Privacy and surveillance
  • Lesson 4 continued: Privacy and surveillance
  • Lesson 5.1: The problem with metrics
  • Lesson 5.2: Our Ecosystem, Venture Capital, & Hypergrowth
  • Lesson 5.3: Losing the Forest for the Trees, guest lecture by Ali Alkhatib
  • Lesson 6: Algorithmic Colonialism, and Next Steps
• Youtube: Lecture 9: Ethics (Full Stack Deep Learning - Spring 2021) 1:04:50
• Youtube: SE4AI: Ethics and Fairness 1:18:37
• Youtube: SE4AI: Security 1:18:24
• Youtube: SE4AI: Safety 1:17:37

Be able to import data from multiple sources

• Docs: Beautiful Soup Documentation
• Datacamp: Importing Data in Python (Part 2)
• Datacamp: Web Scraping in Python

Be able to setup data annotation efficiently

• Article: Create A Synthetic Image Dataset — The “What”, The “Why” and The “How”
• Article: We need Synthetic Data
• Article: Weak Supervision for Online Discussions
• Article: ML Infrastructure Tools for Data Preparation
• Article: Exploring the Role of Human Raters in Creating NLP Datasets
• Article: Inter-Annotator Agreement (IAA)
• Article: How to compute inter-rater reliability metrics (Cohen’s Kappa, Fleiss’s Kappa, Cronbach Alpha, Krippendorff Alpha, Scott’s Pi, Inter-class correlation) in Python
• Article: The Pitfalls of Inter-Rater Reliability in Data Labeling and Machine Learning
• Youtube: Snorkel: Dark Data and Machine Learning - Christopher Ré
• Youtube: Training a NER Model with Prodigy and Transfer Learning
• Youtube: Training a New Entity Type with Prodigy – annotation powered by active learning
• Youtube: ECCV 2020 WSL tutorial: 4. Human-in-the-loop annotations
• Youtube: Active Learning: Why Smart Labeling is the Future of Data Annotation | Alectio
• Youtube: Lecture 8: Data Management (Full Stack Deep Learning - Spring 2021) 0:59:42
• Youtube: Lab 6: Data Labeling (Full Stack Deep Learning - Spring 2021) 0:05:06
• Youtube: Lecture 6: Data Management
• Youtube: SE4AI: Data Quality 1:07:15
• Youtube: SE4AI: Data Programming and Intro to Big Data Processing 0:33:04
• Youtube: SE4AI: Managing and Processing Large Datasets 1:21:27

Be able to manipulate data with Numpy

• Article: A Visual Intro to NumPy and Data Representation
• Article: Good practices with numpy random number generators
• Article: NumPy Illustrated: The Visual Guide to NumPy
• Article: NumPy Fundamentals for Data Science and Machine Learning
• Datacamp: Intro to Python for Data Science
• Pluralsight: Working with Multidimensional Data Using NumPy

Be able to manipulate data with Pandas

• Article: Visualizing Pandas' Pivoting and Reshaping Functions
• Article: A Gentle Visual Intro to Data Analysis in Python Using Pandas
• Article: Comprehensive Guide to Grouping and Aggregating with Pandas
• Article: 8 Python Pandas Value_counts() tricks that make your work more efficient
• Datacamp: pandas Foundations
• Datacamp: Pandas Joins for Spreadsheet Users
• Datacamp: Manipulating DataFrames with pandas
• Datacamp: Merging DataFrames with pandas
• Datacamp: Data Manipulation with pandas
• Datacamp: Optimizing Python Code with pandas
• Datacamp: Streamlined Data Ingestion with pandas
• Datacamp: Analyzing Marketing Campaigns with pandas
• edX: Implementing Predictive Analytics with Spark in Azure HDInsight
• Article: Modern Pandas
  • Modern Pandas (Part 1)
  • Modern Pandas (Part 2)
  • Modern Pandas (Part 3)
  • Modern Pandas (Part 4)
  • Modern Pandas (Part 5)
  • Modern Pandas (Part 6)
  • Modern Pandas (Part 7)
  • Modern Pandas (Part 8)

Be able to manipulate data in spreadsheets

• Datacamp: Spreadsheet basics
• Datacamp: Data Analysis with Spreadsheets
• Datacamp: Intermediate Spreadsheets for Data Science
• Datacamp: Pivot Tables with Spreadsheets
• Datacamp: Data Visualization in Spreadsheets
• Datacamp: Introduction to Statistics in Spreadsheets
• Datacamp: Conditional Formatting in Spreadsheets
• Datacamp: Marketing Analytics in Spreadsheets
• Datacamp: Error and Uncertainty in Spreadsheets
• edX: Analyzing and Visualizing Data with Excel

Be able to manipulate data in databases

• Codecademy: SQL Track
• Datacamp: Intro to SQL for Data Science
• Datacamp: Introduction to MongoDB in Python
• Datacamp: Intermediate SQL
• Datacamp: Exploratory Data Analysis in SQL
• Datacamp: Joining Data in PostgreSQL
• Datacamp: Querying with TransactSQL
• Datacamp: Introduction to Databases in Python
• Datacamp: Reporting in SQL
• Datacamp: Applying SQL to Real-World Problems
• Datacamp: Analyzing Business Data in SQL
• Datacamp: Data-Driven Decision Making in SQL
• Datacamp: Database Design
• Udacity: SQL for Data Analysis
• Udacity: Intro to relational database
• Udacity: Database Systems Concepts & Design

Be able to use Linux

• Article: Streamline your projects using Makefile
• Article: Understand Linux Load Averages and Monitor Performance of Linux
• Article: Command-line Tools can be 235x Faster than your Hadoop Cluster
• Calmcode: makefiles
• Calmcode: entr
• Codecademy: Learn the Command Line
• Datacamp: Introduction to Shell for Data Science
• Datacamp: Introduction to Bash Scripting
• Datacamp: Data Processing in Shell
• MIT: The Missing Semester of CS Education
  • Lecture 1: Course Overview + The Shell (2020) 0:48:16
  • Lecture 2: Shell Tools and Scripting (2020) 0:48:55
  • Lecture 3: Editors (vim) (2020) 0:48:26
  • Lecture 4: Data Wrangling (2020) 0:50:03
  • Lecture 5: Command-line Environment (2020) 0:56:06
  • Lecture 6: Version Control (git) (2020) 1:24:59
  • Lecture 7: Debugging and Profiling (2020) 0:54:13
  • Lecture 8: Metaprogramming (2020) 0:49:52
  • Lecture 9: Security and Cryptography (2020) 1:00:59
  • Lecture 10: Potpourri (2020) 0:57:54
  • Lecture 11: Q&A (2020) 0:53:52
• Thoughtbot: Mastering the Shell
• Thoughtbot: tmux
• Udacity: Linux Command Line Basics
• Udacity: Shell Workshop
• Udacity: Configuring Linux Web Servers
• Web Bos: Command Line Power User
• Youtube: GNU Parallel

Be able to perform feature selection and engineering

• Article: Tips for Advanced Feature Engineering
• Article: Preparing data for a machine learning model
• Article: Feature selection for a machine learning model
• Article: Learning from imbalanced data
• Article: Hacker's Guide to Data Preparation for Machine Learning
• Article: Practical Guide to Handling Imbalanced Datasets
• Datacamp: Analyzing Social Media Data in Python
• Datacamp: Dimensionality Reduction in Python
• Datacamp: Preprocessing for Machine Learning in Python
• Datacamp: Data Types for Data Science
• Datacamp: Cleaning Data in Python
• Datacamp: Feature Engineering for Machine Learning in Python
• Datacamp: Importing & Managing Financial Data in Python
• Datacamp: Manipulating Time Series Data in Python
• Datacamp: Working with Geospatial Data in Python
• Datacamp: Analyzing IoT Data in Python
• Datacamp: Dealing with Missing Data in Python
• Datacamp: Exploratory Data Analysis in Python
• edX: Data Science Essentials
• Udacity: Creating an Analytical Dataset
• Youtube: Applied ML 2020 - 04 - Preprocessing 1:07:40
• Youtube: Applied ML 2020 - 11 - Model Inspection and Feature Selection 1:15:15

Be able to experiment in a notebook

• Article: Securely storing configuration credentials in a Jupyter Notebook
• Article: Automatically Reload Modules with %autoreload
• Calmcode: ipywidgets
• Documentation: Jupyter Lab
• Pluralsight: Getting Started with Jupyter Notebook and Python
• Youtube: William Horton - A Brief History of Jupyter Notebooks
• Youtube: I Like Notebooks
• Youtube: I don't like notebooks.- Joel Grus (Allen Institute for Artificial Intelligence)
• Youtube: Ryan Herr - After model.fit, before you deploy| JupyterCon 2020
• Youtube: nbdev live coding with Hamel Husain
• Youtube: How to Use JupyterLab

Be able to visualize data

• Article: Creating a Catchier Word Cloud Presentation
• Article: Effectively Using Matplotlib
• Article: Which color scale to use when visualizing data
• Datacamp: Introduction to Data Visualization with Python
• Datacamp: Introduction to Seaborn
• Datacamp: Introduction to Matplotlib
• Datacamp: Intermediate Data Visualization with Seaborn
• Datacamp: Visualizing Time Series Data in Python
• Datacamp: Improving Your Data Visualizations in Python
• Datacamp: Visualizing Geospatial Data in Python
• Datacamp: Interactive Data Visualization with Bokeh
• Youtube: Applied ML 2020 - 02 Visualization and matplotlib 1:07:30

Be able to do literature review using research papers

• Paper: A Neural Probabilistic Language Model
• Paper: Efficient Estimation of Word Representations in Vector Space
• Paper: Sequence to Sequence Learning with Neural Networks
• Paper: Neural Machine Translation by Jointly Learning to Align and Translate
• Paper: Attention Is All You Need
• Paper: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Paper: XLNet: Generalized Autoregressive Pretraining for Language Understanding
• Paper: Synonyms Based Term Weighting Scheme: An Extension to TF.IDF
• Paper: RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Paper: GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
• Paper: Amazon.com Recommendations Item-to-Item Collaborative Filtering
• Paper: Collaborative Filtering for Implicit Feedback Datasets
• Paper: BPR: Bayesian Personalized Ranking from Implicit Feedback
• Paper: Factorization Machines
• Paper: Wide & Deep Learning for Recommender Systems
• Paper: Neural Factorization Machines for Sparse Predictive Analytics
• Paper: Multiword Expressions: A Pain in the Neck for NLP
• Paper: PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Paper: ALBERT: A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS
• Paper: Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Paper: A Simple Framework for Contrastive Learning of Visual Representations
• Paper: Self-Supervised Learning of Pretext-Invariant Representations
• Paper: FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Paper: Self-Labelling via Simultalaneous Clustering and Representation Learning
• Paper: A survey on Semi-, Self- and Unsupervised Techniques in Image Classification
• Paper: Multi-document Summarization by using TextRank and Maximal Marginal Relevance for Text in Bahasa Indonesia
• Paper: Train Once, Test Anywhere: Zero-Shot Learning for Text Classification
• Paper: Zero-shot Text Classification With Generative Language Models
• Paper: How to Fine-Tune BERT for Text Classification?
• Paper: Universal Sentence Encoder
• Paper: Enriching Word Vectors with Subword Information
• Paper: Beyond Accuracy: Behavioral Testing of NLP models with CheckList
• Paper: Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks
• Paper: Temporal Ensembling for Semi-Supervised Learning
• Paper: Boosting Self-Supervised Learning via Knowledge Transfer
• Paper: Follow-up Question Generation
• Paper: The Hardware Lottery
• Paper: Question Generation via Overgenerating Transformations and Ranking
• Paper: Good Question! Statistical Ranking for Question Generation
• Paper: Towards ML Engineering: A Brief History Of TensorFlow Extended (TFX)
• Paper: Neural Text Generation: A Practical Guide
• Paper: Pest Management In Cotton Farms: An AI-System Case Study from the Global South
• Paper: BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search
• Paper: On the surprising similarities between supervised and self-supervised models
• Paper: All-but-the-Top: Simple and Effective Postprocessing for Word Representations
• Paper: Simple and Effective Dimensionality Reduction for Word Embeddings
• Paper: AutoCompete: A Framework for Machine Learning Competitions
• Paper: Cost-effective Deployment of BERT Models in Serverless Environment
• Paper: Evaluating Large Language Models Trained on Code
• Paper: What Does BERT Learn about the Structure of Language?
• Paper: What do RNN Language Models Learn about Filler–Gap Dependencies?
• Paper: Symbol Grounding and its Implications for Artificial Intelligence
• Paper: Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world
• Paper: MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
• Paper: Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs
• Paper: Show and Tell: A Neural Image Caption Generator
• Paper: The Curious Case of Neural Text Degeneration
• Youtube: mixup: Beyond Empirical Risk Minimization (Paper Explained)

Be able to model problems mathematically

• 3Blue1Brown: Essence of Calculus
  • The Essence of Calculus, Chapter 1 0:17:04
  • The paradox of the derivative | Essence of calculus, chapter 2 0:17:57
  • Derivative formulas through geometry | Essence of calculus, chapter 3 0:18:43
  • Visualizing the chain rule and product rule | Essence of calculus, chapter 4 0:16:52
  • What's so special about Euler's number e? | Essence of calculus, chapter 5 0:13:50
  • Implicit differentiation, what's going on here? | Essence of calculus, chapter 6 0:15:33
  • Limits, L'Hôpital's rule, and epsilon delta definitions | Essence of calculus, chapter 7 0:18:26
  • Integration and the fundamental theorem of calculus | Essence of calculus, chapter 8 0:20:46
  • What does area have to do with slope? | Essence of calculus, chapter 9 0:12:39
  • Higher order derivatives | Essence of calculus, chapter 10 0:05:38
  • Taylor series | Essence of calculus, chapter 11 0:22:19
  • What they won't teach you in calculus 0:16:22
• 3Blue1Brown: Essence of linear algebra
  • Vectors, what even are they? | Essence of linear algebra, chapter 1 0:09:52
  • Linear combinations, span, and basis vectors | Essence of linear algebra, chapter 2 0:09:59
  • Linear transformations and matrices | Essence of linear algebra, chapter 3 0:10:58
  • Matrix multiplication as composition | Essence of linear algebra, chapter 4 0:10:03
  • Three-dimensional linear transformations | Essence of linear algebra, chapter 5 0:04:46
  • The determinant | Essence of linear algebra, chapter 6 0:10:03
  • Inverse matrices, column space and null space | Essence of linear algebra, chapter 7 0:12:08
  • Nonsquare matrices as transformations between dimensions | Essence of linear algebra, chapter 8 0:04:27
  • Dot products and duality | Essence of linear algebra, chapter 9 0:14:11
  • Cross products | Essence of linear algebra, Chapter 10 0:08:53
  • Cross products in the light of linear transformations | Essence of linear algebra chapter 11 0:13:10
  • Cramer's rule, explained geometrically | Essence of linear algebra, chapter 12 0:12:12
  • Change of basis | Essence of linear algebra, chapter 13 0:12:50
  • Eigenvectors and eigenvalues | Essence of linear algebra, chapter 14 0:17:15
  • Abstract vector spaces | Essence of linear algebra, chapter 15 0:16:46
• 3Blue1Brown: Neural networks
  • But what is a Neural Network? | Deep learning, chapter 1 0:19:13
  • Gradient descent, how neural networks learn | Deep learning, chapter 2 0:21:01
  • What is backpropagation really doing? | Deep learning, chapter 3 0:13:54
  • Backpropagation calculus | Deep learning, chapter 4 0:10:17
• Article: A Visual Tour of Backpropagation
• Article: Entropy, Cross Entropy, and KL Divergence
• Article: Interview Guide to Probability Distributions
• Article: Introduction to Linear Algebra for Applied Machine Learning with Python
• Article: Entropy of a probability distribution — in layman’s terms
• Article: KL Divergence — in layman’s terms
• Article: Probability Distributions
• Article: Relearning Matrices as Linear Functions
• Article: You Could Have Come Up With Eigenvectors - Here's How
• Article: PageRank - How Eigenvectors Power the Algorithm Behind Google Search
• Article: Interactive Visualization of Why Eigenvectors Matter
• Article: Cross-Entropy and KL Divergence
• Article: Why Randomness Is Information?
• Article: Basic Probability Theory
• Article: Math You Need to Succeed In ML Interviews
• Book: Basics of Linear Algebra for Machine Learning
• Datacamp: Introduction to Statistics in Python
• Datacamp: Foundations of Probability in Python
• Datacamp: Statistical Thinking in Python (Part 1)
• Datacamp: Statistical Thinking in Python (Part 2)
• Datacamp: Statistical Simulation in Python
• edX: Essential Statistics for Data Analysis using Excel
• Computational Linear Algebra for Coders
• Khan Academy: Precalculus
• Khan Academy: Probability
• Khan Academy: Differential Calculus
• Khan Academy: Multivariable Calculus
• Khan Academy: Linear Algebra
• MIT: 18.06 Linear Algebra (Professor Strang)
  • 1. The Geometry of Linear Equations 0:39:49
  • 2. Elimination with Matrices. 0:47:41
  • 3. Multiplication and Inverse Matrices 0:46:48
  • 4. Factorization into A = LU 0:48:05
  • 5. Transposes, Permutations, Spaces R^n 0:47:41
  • 6. Column Space and Nullspace 0:46:01
  • 9. Independence, Basis, and Dimension 0:50:14
  • 10. The Four Fundamental Subspaces 0:49:20
  • 11. Matrix Spaces; Rank 1; Small World Graphs 0:45:55
  • 14. Orthogonal Vectors and Subspaces 0:49:47
  • 15. Projections onto Subspaces 0:48:51
  • 16. Projection Matrices and Least Squares 0:48:05
  • 17. Orthogonal Matrices and Gram-Schmidt 0:49:09
  • 21. Eigenvalues and Eigenvectors 0:51:22
  • 22. Diagonalization and Powers of A 0:51:50
  • 24. Markov Matrices; Fourier Series 0:51:11
  • 25. Symmetric Matrices and Positive Definiteness 0:43:52
  • 27. Positive Definite Matrices and Minima 0:50:40
  • 29. Singular Value Decomposition 0:40:28
  • 30. Linear Transformations and Their Matrices 0:49:27
  • 31. Change of Basis; Image Compression 0:50:13
  • 33. Left and Right Inverses; Pseudoinverse 0:41:52
• StatQuest: Statistics Fundamentals
  • StatQuest: Histograms, Clearly Explained 0:03:42
  • StatQuest: What is a statistical distribution? 0:05:14
  • StatQuest: The Normal Distribution, Clearly Explained!!! 0:05:12
  • Statistics Fundamentals: Population Parameters 0:14:31
  • Statistics Fundamentals: The Mean, Variance and Standard Deviation 0:14:22
  • StatQuest: What is a statistical model? 0:03:45
  • StatQuest: Sampling A Distribution 0:03:48
  • Hypothesis Testing and The Null Hypothesis 0:14:40
  • Alternative Hypotheses: Main Ideas!!! 0:09:49
  • p-values: What they are and how to interpret them 0:11:22
  • How to calculate p-values 0:25:15
  • p-hacking: What it is and how to avoid it! 0:13:44
  • Statistical Power, Clearly Explained!!! 0:08:19
  • Power Analysis, Clearly Explained!!! 0:16:44
  • Covariance and Correlation Part 1: Covariance 0:22:23
  • Covariance and Correlation Part 2: Pearson's Correlation 0:19:13
  • StatQuest: R-squared explained 0:11:01
  • The Central Limit Theorem 0:07:35
  • StatQuickie: Standard Deviation vs Standard Error 0:02:52
  • StatQuest: The standard error 0:11:43
  • StatQuest: Technical and Biological Replicates 0:05:27
  • StatQuest - Sample Size and Effective Sample Size, Clearly Explained 0:06:32
  • Bar Charts Are Better than Pie Charts 0:01:45
  • StatQuest: Boxplots, Clearly Explained 0:02:33
  • StatQuest: Logs (logarithms), clearly explained 0:15:37
  • StatQuest: Confidence Intervals 0:06:41
  • StatQuickie: Thresholds for Significance 0:06:40
  • StatQuickie: Which t test to use 0:05:10
  • StatQuest: One or Two Tailed P-Values 0:07:05
  • The Binomial Distribution and Test, Clearly Explained!!! 0:15:46
  • StatQuest: Quantiles and Percentiles, Clearly Explained!!! 0:06:30
  • StatQuest: Quantile-Quantile Plots (QQ plots), Clearly Explained 0:06:55
  • StatQuest: Quantile Normalization 0:04:51
  • StatQuest: Probability vs Likelihood 0:05:01
  • StatQuest: Maximum Likelihood, clearly explained!!! 0:06:12
  • Maximum Likelihood for the Exponential Distribution, Clearly Explained! V2.0 0:09:39
  • Why Dividing By N Underestimates the Variance 0:17:14
  • Maximum Likelihood for the Binomial Distribution, Clearly Explained!!! 0:11:24
  • Maximum Likelihood For the Normal Distribution, step-by-step! 0:19:50
  • StatQuest: Odds and Log(Odds), Clearly Explained!!! 0:11:30
  • StatQuest: Odds Ratios and Log(Odds Ratios), Clearly Explained!!! 0:16:20
  • Live 2020-04-20!!! Expected Values 0:33:00
• Udacity: Eigenvectors and Eigenvalues
• Udacity: Linear Algebra Refresher
• Udacity: Statistics
• Udacity: Intro to Descriptive Statistics
• Udacity: Intro to Inferential Statistics

Be able to setup project structure

• Article: pydantic
• Article: Organizing machine learning projects: project management guidelines
• Article: Logging and Debugging in Machine Learning - How to use Python debugger and the logging module to find errors in your AI application
• Article: Best practices to write Deep Learning code: Project structure, OOP, Type checking and documentation
• Article: Configuring Google Colab Like A Pro
• Article: Stop using print, start using loguru in Python
• Article: Hypermodern Python
• Article: Hypermodern Python Chapter 2: Testing
• Article: Hypermodern Python Chapter 3: Linting
• Article: Hypermodern Python Chapter 4: Typing
• Article: Hypermodern Python Chapter 5: Documentation
• Article: Hypermodern Python Chapter 6: CI/CD
• Article: Push and pull: when and why to update your dependencies
• Article: Reproducible and upgradable Conda environments: dependency management with conda-lock
• Article: Options for packaging your Python code: Wheels, Conda, Docker, and more
• Article: Making model training scripts robust to spot interruptions
• Calmcode: logging
• Calmcode: tqdm
• Calmcode: virtualenv
• Coursera: Structuring Machine Learning Projects
• Doc: Python Lifecycle Training
• Datacamp: Introduction to Data Engineering
• Datacamp: Conda Essentials
• Datacamp: Conda for Building & Distributing Packages
• Datacamp: Software Engineering for Data Scientists in Python
• Datacamp: Designing Machine Learning Workflows in Python
• Datacamp: Object-Oriented Programming in Python
• Datacamp: Command Line Automation in Python
• Datacamp: Creating Robust Python Workflows
• Developing Python Packages
• Treehouse: Object Oriented Python
• Treehouse: Setup Local Python Environment
• Udacity: Writing READMEs
• Youtube: Lecture 1: Introduction to Deep Learning
• Youtube: Lecture 2: Setting Up Machine Learning Projects
• Youtube: Lecture 3: Introduction to the Text Recognizer Project
• Youtube: Lecture 4: Infrastructure and Tooling
• Youtube: Hydra configuration
• Youtube: Continuous integration
• Youtube: Data Engineering + ML + Software Engineering // Satish Chandra Gupta // MLOps Coffee Sessions #16
• Youtube: OO Design and Testing Patterns for Machine Learning with Chris Gerpheide
• Youtube: Tutorial: Sebastian Witowski - Modern Python Developer's Toolkit
• Youtube: Lecture 13: ML Teams (Full Stack Deep Learning - Spring 2021) 0:58:13
• Youtube: Lecture 5: ML Projects (Full Stack Deep Learning - Spring 2021) 1:13:14
• Youtube: Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021) 1:07:21

Be able to version control code

• Article: Mastering Git Stash Workflow
• Article: How to Become a Master of Git Tags
• Article: How to track large files in Github / Bitbucket? Git LFS to the rescue
• Article: Keep your git directory clean with git clean and git trash
• Codecademy: Learn Git
• Code School: Git Real
• Datacamp: Introduction to Git for Data Science
• Thoughtbot: Mastering Git
• Udacity: GitHub & Collaboration
• Udacity: How to Use Git and GitHub
• Udacity: Version Control with Git
• Youtube: 045 Introduction to Git LFS
• Youtube: Git & Scripting

Be able to version control data

• Youtube: DVC Basics
  • Versioning Data with DVC (Hands-On Tutorial!) 0:13:04
  • Sharing Data and Models with DVC (Hands-On Data Science Tutorial!) 0:08:53
• Article: ML Ops: Data Science Version Control
• Youtube: Data versioning in machine learning projects - Dmitry Petrov 0:34:44
• Zoom: Data versioning with DVC Part 1
• Zoom: Data versioning with DVC Part 2

Be able to use experiment management tools

• Article: Supercharge your Training with Pytorch Lightning + Weights & Biases
• Article: Storing Metadata from Machine Learning Experiments
• Youtube: Weights and Biases Tutorial
• Youtube: Integrate Weights & Biases with PyTorch
• Youtube: Log (Almost) Anything with Weights & Biases
• Youtube: Lab 5: Experiment Management (Full Stack Deep Learning - Spring 2021) 0:30:41
• Youtube: Lecture 5: Tracking Experiments
• Youtube: Weight & Biases
• Youtube: SE4AI: Versioning, Provenance, and Reproducibility 1:18:29

Be able to setup model validation

• Article: Evaluating a machine learning model
• Article: Validating your Machine Learning Model
• Article: Measuring Performance: AUPRC and Average Precision
• Article: Measuring Performance: AUC (AUROC)
• Article: Measuring Performance: The Confusion Matrix
• Article: Measuring Performance: Accuracy
• Article: ROC Curves: Intuition Through Visualization
• Article: Precision, Recall, Accuracy, and F1 Score for Multi-Label Classification
• Article: The Complete Guide to AUC and Average Precision: Simulations and Visualizations
• Article: Best Use of Train/Val/Test Splits, with Tips for Medical Data
• Article: The correct way to evaluate online machine learning models
• Article: Proxy Metrics
• Youtube: Accuracy as a Failure
• Youtube: Applied ML 2020 - 09 - Model Evaluation and Metrics 1:18:23
• Youtube: Machine Learning Fundamentals: Cross Validation 0:06:04
• Youtube: Machine Learning Fundamentals: The Confusion Matrix 0:07:12
• Youtube: Machine Learning Fundamentals: Sensitivity and Specificity 0:11:46
• Youtube: Machine Learning Fundamentals: Bias and Variance 0:06:36
• Youtube: ROC and AUC, Clearly Explained! 0:16:26

Be familiar with inner working of models

• Article: Naive Bayes classification
• Article: Linear regression
• Article: Polynomial regression
• Article: Logistic regression
• Article: Decision trees
• Article: K-nearest neighbors
• Article: Support Vector Machines
• Article: Random forests
• Article: Boosted trees
• Article: Hacker's Guide to Fundamental Machine Learning Algorithms with Python
• Article: Neural networks: activation functions
• Article: Neural networks: training with backpropagation
• Article: Neural Network from scratch-part 1
• Article: Neural Network from scratch-part 2
• Article: Perceptron to Deep-Neural-Network
• Article: One-vs-Rest strategy for Multi-Class Classification
• Article: Multi-class Classification — One-vs-All & One-vs-One
• Article: One-vs-Rest and One-vs-One for Multi-Class Classification
• Article: Deep Learning Algorithms - The Complete Guide
• Article: Machine Learning Techniques Primer
• AWS: Understanding Neural Networks
• Book: Grokking Deep Learning
• Book: Make Your Own Neural Network
• Coursera: Neural Networks and Deep Learning
• Datacamp: Extreme Gradient Boosting with XGBoost
• Datacamp: Ensemble Methods in Python
• StatQuest: Machine Learning
  • StatQuest: Fitting a line to data, aka least squares, aka linear regression. 0:09:21
  • StatQuest: Linear Models Pt.1 - Linear Regression 0:27:26
  • StatQuest: StatQuest: Linear Models Pt.2 - t-tests and ANOVA 0:11:37
  • StatQuest: Odds and Log(Odds), Clearly Explained!!! 0:11:30
  • StatQuest: Odds Ratios and Log(Odds Ratios), Clearly Explained!!! 0:16:20
  • StatQuest: Logistic Regression 0:08:47
  • Logistic Regression Details Pt1: Coefficients 0:19:02
  • Logistic Regression Details Pt 2: Maximum Likelihood 0:10:23
  • Logistic Regression Details Pt 3: R-squared and p-value 0:15:25
  • Saturated Models and Deviance 0:18:39
  • Deviance Residuals 0:06:18
  • Regularization Part 1: Ridge (L2) Regression 0:20:26
  • Regularization Part 2: Lasso (L1) Regression 0:08:19
  • Ridge vs Lasso Regression, Visualized!!! 0:09:05
  • Regularization Part 3: Elastic Net Regression 0:05:19
  • StatQuest: Principal Component Analysis (PCA), Step-by-Step 0:21:57
  • StatQuest: PCA main ideas in only 5 minutes!!! 0:06:04
  • StatQuest: PCA - Practical Tips 0:08:19
  • StatQuest: PCA in Python 0:11:37
  • StatQuest: Linear Discriminant Analysis (LDA) clearly explained. 0:15:12
  • StatQuest: MDS and PCoA 0:08:18
  • StatQuest: t-SNE, Clearly Explained 0:11:47
  • StatQuest: Hierarchical Clustering 0:11:19
  • StatQuest: K-means clustering 0:08:57
  • StatQuest: K-nearest neighbors, Clearly Explained 0:05:30
  • Naive Bayes, Clearly Explained!!! 0:15:12
  • Gaussian Naive Bayes, Clearly Explained!!! 0:09:41
  • StatQuest: Decision Trees 0:17:22
  • StatQuest: Decision Trees, Part 2 - Feature Selection and Missing Data 0:05:16
  • Regression Trees, Clearly Explained!!! 0:22:33
  • How to Prune Regression Trees, Clearly Explained!!! 0:16:15
  • StatQuest: Random Forests Part 1 - Building, Using and Evaluating 0:09:54
  • StatQuest: Random Forests Part 2: Missing data and clustering 0:11:53
  • The Chain Rule 0:18:23
  • Gradient Descent, Step-by-Step 0:23:54
  • Stochastic Gradient Descent, Clearly Explained!!! 0:10:53
  • AdaBoost, Clearly Explained 0:20:54
  • Gradient Boost Part 1: Regression Main Ideas 0:15:52
  • Gradient Boost Part 2: Regression Details 0:26:45
  • Gradient Boost Part 3: Classification 0:17:02
  • Gradient Boost Part 4: Classification Details 0:36:59
  • Support Vector Machines, Clearly Explained!!! 0:20:32
  • Support Vector Machines Part 2: The Polynomial Kernel 0:07:15
  • Support Vector Machines Part 3: The Radial (RBF) Kernel 0:15:52
  • XGBoost Part 1: Regression 0:25:46
  • XGBoost Part 2: Classification 0:25:17
  • XGBoost Part 3: Mathematical Details 0:27:24
  • XGBoost Part 4: Crazy Cool Optimizations 0:24:27
  • StatQuest: Fiitting a curve to data, aka lowess, aka loess 0:10:10
  • Statistics Fundamentals: Population Parameters 0:14:31
  • Principal Component Analysis (PCA) clearly explained (2015) 0:20:16
  • Decision Trees in Python from Start to Finish 1:06:23
• Udacity: Classification Models
• Youtube: Neural Networks from Scratch in Python
  • Neural Networks from Scratch - P.1 Intro and Neuron Code 0:16:59
  • Neural Networks from Scratch - P.2 Coding a Layer 0:15:06
  • Neural Networks from Scratch - P.3 The Dot Product 0:25:17
  • Neural Networks from Scratch - P.4 Batches, Layers, and Objects 0:33:46
  • Neural Networks from Scratch - P.5 Hidden Layer Activation Functions 0:40:05
• Youtube: Applied ML 2020 - 03 Supervised learning and model validation 1:12:00
• Youtube: Applied ML 2020 - 05 - Linear Models for Regression 1:06:54
• Youtube: Applied ML 2020 - 06 - Linear Models for Classification 1:07:50
• Youtube: Applied ML 2020 - 07 - Decision Trees and Random Forests 1:07:58
• Youtube: Applied ML 2020 - 08 - Gradient Boosting 1:02:12
• Youtube: Applied ML 2020 - 18 - Neural Networks 1:19:36
• Youtube: Applied ML 2020 - 12 - AutoML (plus some feature selection) 1:25:38

Be able to improve model generalization

• Article: Deep neural networks: preventing overfitting
• Article: Normalizing your data (specifically, input and batch normalization)
• Article: Batch Normalization
• Article: Are Deep Neural Networks Dramatically Overfitted?
• Article: In-layer normalization techniques for training very deep neural networks
• Article: Label Smoothing Explained using Microsoft Excel
• Article: Uncertainty Quantification Part 4: Leveraging Dropout in Neural Networks (CNNs)
• Article: Simple Ways to Tackle Class Imbalance
• Youtube: Applied ML 2020 - 10 - Calibration, Imbalanced data 1:16:14
• Youtube: Lecture 10: Troubleshooting Deep Neural Networks

Be familiar with fundamental ML concepts

• Article: Connections: Log Likelihood, Cross Entropy, KL Divergence, Logistic Regression, and Neural Networks
• Article: MLE and MAP — in layman’s terms
• An overview of gradient descent optimization algorithms
• Article: Optimization for Deep Learning Highlights in 2017
• Article: Gradient descent
• Article: Setting the learning rate of your neural network
• Article: Cross-entropy for classification
• Article: Dismantling Neural Networks to Understand the Inner Workings with Math and Pytorch
• Datacamp: AI Fundamentals
• Datacamp: Foundations of Predictive Analytics in Python (Part 1)
• Datacamp: Foundations of Predictive Analytics in Python (Part 2)
• Elements of AI
• edX: Principles of Machine Learning
• edX: Data Science Essentials
• Fast.ai: Deep Learning for Coder (2020)
  • Lesson 0
  • Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
  • Lesson 5
  • Lesson 6
  • Lesson 7
  • Lesson 8
• Youtube: Deep Double Descent

Be able to implement models in scikit-learn

• Article: Stacking made easy with Sklearn
• Article: Curve Fitting With Python
• Article: A Guide to Calibration Plots in Python
• Calmcode: human-learn
• Datacamp: Supervised Learning with scikit-learn
• Datacamp: Machine Learning with Tree-Based Models in Python
• Datacamp: Introduction to Linear Modeling in Python
• Datacamp: Linear Classifiers in Python
• Datacamp: Generalized Linear Models in Python
• Notebook: scikit-learn tips
• Pluralsight: Building Machine Learning Models in Python with scikit-learn
• Video: human learn
• Youtube: dabl: Automatic Machine Learning with a Human in the Loop 00:25:43
• Youtube: Multilabel and Multioutput Classification -Machine Learning with TensorFlow & scikit-learn on Python
• Youtube: DABL: Automatic machine learning with a human in the loop- AI Latim American SumMIT Day 1

Be able to implement models in Tensorflow and Keras

• Coursera: Introduction to Tensorflow
• Coursera: Convolutional Neural Networks in TensorFlow
• Deeplizard: Keras - Python Deep Learning Neural Network API
• Book: Deep Learning with Python (Page: 276)
• Datacamp: Deep Learning in Python
• Datacamp: Convolutional Neural Networks for Image Processing
• Datacamp: Introduction to TensorFlow in Python
• Datacamp: Introduction to Deep Learning with Keras
• Datacamp: Advanced Deep Learning with Keras
• Google: Machine Learning Crash Course
• Pluralsight: Deep Learning with Keras
• Udacity: Intro to TensorFlow for Deep Learning

Be able to implement models in PyTorch

• Article: Keeping Up with PyTorch Lightning and Hydra
• Article: The One PyTorch Trick Which You Should Know
• Article: How does automatic differentiation really work?
• Article: 7 Tips To Maximize PyTorch Performance
• Article: An introduction to PyTorch Lightning with comparisons to PyTorch
• Article: Converting From Keras To PyTorch Lightning
• Article: From PyTorch to PyTorch Lightning — A gentle introduction
• Article: Introducing PyTorch Lightning Sharded: Train SOTA Models, With Half The Memory
• Article: Sharded: A New Technique To Double The Size Of PyTorch Models
• Article: Understanding Bidirectional RNN in PyTorch
• Article: A developer-friendly guide to mixed precision training with PyTorch
• Article: A developer-friendly guide to model pruning in PyTorch
• Article: A developer-friendly guide to model quantization with PyTorch
• Article: Tricks for training PyTorch models to convergence more quickly
• Article: PyTorch Lightning Bolts — From Linear, Logistic Regression on TPUs to pre-trained GANs
• Article: Scaling Logistic Regression Via Multi-GPU/TPU Training
• Article: Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups
• Article: PyTorch Lightning 0.9 — synced BatchNorm, DataModules and final API!
• Article: PyTorch Lightning: Metrics
• Article: PyTorch Multi-GPU Metrics Library and More in PyTorch Lightning 0.8.1
• Article: Distributed model training in PyTorch using DistributedDataParallel
• Article: Distributed model training in PyTorch using DistributedDataParallel
• Article: EINSUM IS ALL YOU NEED - EINSTEIN SUMMATION IN DEEP LEARNING
• Article: Faster Deep Learning Training with PyTorch – a 2021 Guide
• Article: Fit More and Train Faster With ZeRO via DeepSpeed and FairScale
• Article: PyTorch Lightning V1.2.0- DeepSpeed, Pruning, Quantization, SWA
• Article: But what are PyTorch DataLoaders really?
• Article: Using PyTorch + NumPy? You're making a mistake.
• Article: How Wadhwani AI Uses PyTorch To Empower Cotton Farmers
• Article: Taming LSTMs: Variable-sized mini-batches and why PyTorch is good for your health
• Article: How to Build a Streaming DataLoader with PyTorch
• Article: Transform your ML-model to Pytorch with Hummingbird
• Article: PyTorch Loss Functions: The Ultimate Guide
• Article: Pad pack sequences for Pytorch batch processing with DataLoader
• Article: Model Parallelism
• Notebook: Tensor Arithmetic
• Notebook: Autograd
• Notebook: Optimization
• Notebook: Network modules
• Notebook: Datasets and Dataloaders
• Documentation: Pytorch Lightning
• Datacamp: Introduction to Deep Learning with PyTorch
• Deeplizard: Neural Network Programming - Deep Learning with PyTorch
• Udacity: Intro to Deep Learning with PyTorch
• Youtube: PyTorch Lightning 101
  • Training a classification model on MNIST with PyTorch
  • From PyTorch to PyTorch Lightning
  • Lightning Data Modules
  • PyTorch Dropout, Batch size and interactive debugging
  • Episode 4: Implementing a PyTorch Trainer: PyTorch Lightning Trainer and callbacks under-the-hood
• Youtube: SimCLR with PyTorch Lightning
• Youtube: PyTorch Performance Tuning Guide 26:41:00
• Youtube: Skin Cancer Detection with PyTorch
  • [PART 1] Skin Cancer Detection with PyTorch 0:10:21
  • [PART 2] Skin Cancer Detection with PyTorch 0:21:57
  • [PART 3] Skin Cancer Detection with PyTorch 0:22:24
• Youtube: Learn with Lightning
• Youtube: PyTorch Tutorial - RNN & LSTM & GRU - Recurrent Neural Nets 00:15:51
• Youtube: Pytorch Zero to All
  • PyTorch Lecture 01: Overview 0:10:18
  • PyTorch Lecture 02: Linear Model 0:12:52
  • PyTorch Lecture 03: Gradient Descent 0:08:24
  • PyTorch Lecture 04: Back-propagation and Autograd 0:15:25
  • PyTorch Lecture 05: Linear Regression in the PyTorch way 0:11:50
  • PyTorch Lecture 06: Logistic Regression 0:10:41
  • PyTorch Lecture 07: Wide and Deep 0:10:37
  • PyTorch Lecture 08: PyTorch DataLoader 0:06:41
  • PyTorch Lecture 09: Softmax Classifier 0:18:47
  • PyTorch Lecture 10: Basic CNN 0:15:52
  • PyTorch Lecture 11: Advanced CNN 0:12:58
  • PyTorch Lecture 12: RNN1 - Basics 0:28:47
  • PyTorch Lecture 13: RNN 2 - Classification 0:17:22
• PyTorch Developer Day 2020 | Full Livestream
• Youtube: Lightning Chat: How a Grandmaster Won a Kaggle Competition Using Pytorch Lightning
• Youtube: Production Inference Deployment with PyTorch
• Youtube: What is Automatic Differentiation?
• Youtube: JAX: accelerated machine learning research via composable function transformations in Python

Be able to implement models using cloud services

• AWS: Amazon Transcribe Deep Dive: Using Feedback Loops to Improve Confidence Level of Transcription
• AWS: Build a Text Classification Model with AWS Glue and Amazon SageMaker
• AWS: Deep Dive on Amazon Rekognition: Building Computer Visions Based Smart Applications
• AWS: Hands-on Rekognition: Automated Video Editing
• AWS: Introduction to Amazon Comprehend
• AWS: Introduction to Amazon Comprehend Medical
• AWS: Introduction to Amazon Elastic Inference
• AWS: Introduction to Amazon Forecast
• AWS: Introduction to Amazon Lex
• AWS: Introduction to Amazon Personalize
• AWS: Introduction to Amazon Polly
• AWS: Introduction to Amazon SageMaker Ground Truth
• AWS: Introduction to Amazon SageMaker Neo
• AWS: Introduction to Amazon Transcribe
• AWS: Introduction to Amazon Translate
• AWS: Introduction to AWS Marketplace - Machine Learning Category
• AWS: Machine Learning Exam Basics
• AWS: Neural Machine Translation with Sockeye
• AWS: Process Model: CRISP-DM on the AWS Stack
• AWS: Satellite Image Classification in SageMaker
• Datacamp: Introduction to AWS Boto in Python
• edX: Amazon SageMaker: Simplifying Machine Learning Application Development

Be able to apply unsupervised learning algorithms

• Article: Decrypt Generative Adversarial Networks (GAN)
• Article: GANs in computer vision - Conditional image synthesis and 3D object generation
• Article: GANs in computer vision - Improved training with Wasserstein distance, game theory control and progressively growing schemes
• Article: GANs in computer vision - Introduction to generative learning
• Article: GANs in computer vision - self-supervised adversarial training and high-resolution image synthesis with style incorporation
• Article: GANs in computer vision - semantic image synthesis and learning a generative model from a single image
• Article: Paper Summary: DeViSE: A Deep Visual-Semantic Embedding Model
• Article: Contrastive Self-Supervised Learning
• Article: From Autoencoder to Beta-VAE
• Article: Self-Supervised Representation Learning
• Article: Self-supervised learning: The dark matter of intelligence
• Article: Understanding self-supervised and contrastive learning with "Bootstrap Your Own Latent" (BYOL)
• Article: How to Generate Images using Autoencoders
• Article: Introduction to autoencoders
• Article: Soft clustering with Gaussian mixed models (EM)
• Article: Variational autoencoders
• Article: Build a simple Image Retrieval System with an Autoencoder
• Article: Deep Inside Autoencoders
• Article: An overview of proxy-label approaches for semi-supervised learning
• Article: From Research to Production with Deep Semi-Supervised Learning
• Article: Affinity Propagation Algorithm Explained
• Article: Algorithm Breakdown: Affinity Propagation
• Article: Create, Visualize and Interpret Customer Segments
• Article: A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
• Article: EfficientDet Meets Pytorch-Lightning
• Article: Principal components analysis (PCA)
• Article: RecSys 2020 - Takeaways and Notable Papers
• Article: Grouping data points with k-means clustering
• Article: A gentle introduction to HDBSCAN and density-based clustering
• Article: Deepfakes: Face synthesis with GANs and Autoencoders
• Article: The 3 Deep Learning Frameworks For End-to-End Speech Recognition That Power Your Devices
• Article: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• Berkeley: Deep Unsupervised Learning Spring 2020
  • L1 Introduction -- CS294-158-SP20 Deep Unsupervised Learning -- UC Berkeley, Spring 2020 1:10:02
  • L2 Autoregressive Models -- CS294-158-SP20 Deep Unsupervised Learning -- UC Berkeley, Spring 2020 2:27:23
  • L3 Flow Models -- CS294-158-SP20 Deep Unsupervised Learning -- UC Berkeley -- Spring 2020 1:56:53
  • L4 Latent Variable Models (VAE) -- CS294-158-SP20 Deep Unsupervised Learning -- UC Berkeley 2:19:33
  • Lecture 5 Implicit Models -- GANs Part I --- UC Berkeley, Spring 2020 2:32:32
  • Lecture 6 Implicit Models / GANs part II --- CS294-158-SP20 Deep Unsupervised Learning -- Berkeley 2:09:14
  • Lecture 7 Self-Supervised Learning -- UC Berkeley Spring 2020 - CS294-158 Deep Unsupervised Learning 2:20:41
  • L8 Round-up of Strengths and Weaknesses of Unsupervised Learning Methods -- UC Berkeley SP20 0:41:51
  • L9 Semi-Supervised Learning and Unsupervised Distribution Alignment -- CS294-158-SP20 UC Berkeley 2:16:00
  • L10 Compression -- UC Berkeley, Spring 2020, CS294-158 Deep Unsupervised Learning 3:09:49
  • L11 Language Models -- guest instructor: Alec Radford (OpenAI) --- Deep Unsupervised Learning SP20 2:38:19
  • L12 Representation Learning for Reinforcement Learning --- CS294-158 UC Berkeley Spring 2020 2:01:56
• Datacamp: Customer Segmentation in Python
• Datacamp: Unsupervised Learning in Python
• Deck: Demystifying Self-Supervised Learning for Visual Recognition
• DeepMind: Inefficient Data Efficiency
• Google: Clustering
• Udacity: Segmentation and Clustering
• Wandb: Unsupervised Visual Representation Learning with SwAV
• Youtube: Applied ML 2020 - 14 - Clustering and Mixture Models 1:26:33
• Youtube: Applied ML 2020 - 13 - Dimensionality reduction 1:30:34
• Youtube: BYOL: Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (Paper Explained)
• Youtube: A critical analysis of self-supervision, or what we can learn from a single image (Paper Explained)
• Youtube: Week 10 – Lecture: Self-supervised learning (SSL) in computer vision (CV)
• Youtube: CVPR 2020 Tutorial: Towards Annotation-Efficient Learning
• Youtube: Yuki Asano | Self-Supervision | Self-Labelling | Labelling Unlabelled videos | CV | CTDS.Show #81
• Youtube: Contrastive Clustering with SwAV
• Youtube: Variational Autoencoders - EXPLAINED! 0:17:36
• Youtube: OptaProAnalyticsForum– Learning to watch football: Self-supervised representations for tracking data
• Youtube: Can a Neural Net tell if an image is mirrored? – Visual Chirality
• Youtube: Deep InfoMax: Learning deep representations by mutual information estimation and maximization
• Deep Learning Lecture Summer 2020
  • Deep Learning: Unsupervised Learning - Part 1
  • Deep Learning: Unsupervised Learning - Part 2
  • Deep Learning: Unsupervised Learning - Part 3
  • Deep Learning: Unsupervised Learning - Part 4
  • Deep Learning: Unsupervised Learning - Part 5
  • Deep Learning: Weakly and Self-Supervised Learning - Part 1
  • Deep Learning: Weakly and Self-Supervised Learning - Part 2
  • Deep Learning: Weakly and Self-Supervised Learning - Part 3
  • Deep Learning: Weakly and Self-Supervised Learning - Part 4
• ECCV 2020: New Frontiers for Learning with Limited Labels or Data
  • Introduction to New Frontiers on Learning with Limited Labels or Data
  • Self-Supervised Part and Viewpoint Discovery from Image Collections
  • Learning Visual Correspondences across Instances and Video Frames
  • Limitless Labels in a Labelless World: Weak Supervision with Noisy Labels
• Youtube: Self-Supervised Learning - What is Next? - Workshop at ECCV 2020, August 28th
  • Next Challenges for Self-Supervised Learning - Aäron van den Oord 0:20:13
  • Perspectives on Unsupervised Representation Learning - Paolo Favaro 0:42:41
  • Learning and Transferring Visual Representations with Few Labels - Carl Doersch 0:32:53
  • Self-Supervision as a Path to a Post-Dataset Era - Alexei Alyosha Efros 0:38:06
• Youtube: Marco Cuturi - A Primer on Optimal Transport
• Youtube: Sebastian Ruder: Neural Semi-supervised Learning under Domain Shift
• Youtube: Clustering Algorithms

Be able to implement NLP models

• Article: Fixing common Unicode mistakes with Python – after they’ve been made
• Article: 10 Popular Keyword Extraction Algorithms in Natural Language Processing
• Article: Deconstructing BERT
• Article: How To Create Data Products That Are Magical Using Sequence-to-Sequence Models
• Article: Why Rasa uses Sparse Layers in Transformers
• Article: Semantic Search On Documents
• Article: Locality-sensitive Hashing and Singular to Plural Noun Conversion
• Article: Build A Keyword Extraction API with Spacy, Flask, and FuzzyWuzzy
• Article: What is Hidden in the Hidden Markov Model?
• Article: Unsupervised NER using BERT
• Article: Unsupervised creation of interpretable sentence representations
• Article: Unsupervised synonym harvesting
• Article: Zero shot NER using RoBERTA
• Article: Maximizing BERT model performance
• Article: Swiss army knife for unsupervised task solving
• Article: 10 Exciting Ideas of 2018 in NLP
• Article: 74 Summaries of Machine Learning and NLP Research
• Article: Advance BERT model via transferring knowledge from Cross-Encoders to Bi-Encoders
• Article: Learning to select data for transfer learning
• Article: T5 — a model that explores the limits of transfer learning
• Article: The State of Transfer Learning in NLP
• Article: Haystack: The State of Search in 2021
• Article: How to build a State-of-the-Art Conversational AI with Transfer Learning
• Article: Commonsense Reasoning for Natural Language Processing
• Article: Language Models
• Article: Paraphrasing
• Article: Poor man’s GPT-3: Few shot text generation with T5 Transformer
• Article: Text Generation
• Article: Controlling Text Generation with Plug and Play Language Models
• Article: What makes a good conversation?
• Article: How to steal modern NLP systems with gibberish?
• Article: Intuition & Use-Cases of Embeddings in NLP & beyond
• Article: The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning)
• Article: The Illustrated GPT-2 (Visualizing Transformer Language Models)
• Article: The Illustrated Transformer
• Article: The Illustrated Word2vec
• Article: A Deep Dive into the Reformer
• Article: A Survey of Long-Term Context in Transformers
• Article: Large Memory Layers with Product Keys
• Article: Optimal Transport and the Sinkhorn Transformer
• Article: Pattern-Exploiting Training
• Article: Talking-Heads Attention
• Article: How to Apply BERT to Arabic and Other Languages
• Article: Neural Language Models as Domain-Specific Knowledge Bases
• Article: Domain-Specific BERT Models
• Article: Existing Tools for Named Entity Recognition
• Article: Smart Batching Tutorial - Speed Up BERT Training
• Article: Attention? An Other Perspective!: Part 2
• Article: Attention? An Other Perspective!: Part 3
• Article: Attention? An Other Perspective!: Part 4
• Article: Attention? An Other Perspective!: Part 5
• Article: Attention? An Other Perspective!: Part 1
• Article: Rebuilding the spellchecker, pt.4: Introduction to suggest algorithm
• Article: Rebuilding the spellchecker: Hunspell and the order of edits
• Article: Rebuilding the most popular spellchecker. Part 1
• Article: Rebuilding the spellchecker, pt.2: Just look in the dictionary, they said!
• Article: Rebuilding the spellchecker, pt.3: Lookup—compounds and solutions
• Article: Automatic Topic Labeling in 2018: History and Trends
• Article: Deep Learning for NLP Best Practices
• Article: Attention and Memory in Deep Learning and NLP
• Article: Long Short-Term Memory: From Zero to Hero with PyTorch
• Article: Ten trends in Deep learning NLP
• Article: The Illustrated Wav2vec
• Article: A Review of the Neural History of Natural Language Processing
• Article: ColumnTransformer Meets Natural Language Processing
• Article: Neural Transfer Learning for Natural Language Processing
• Article: Tracking the Progress in Natural Language Processing
• Article: Implementing Bengio’s Neural Probabilistic Language Model (NPLM) using Pytorch
• Article: Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models
• Article: How many data points is a prompt worth?
• Article: NLP: Pre-trained Sentiment Analysis
• Article: Transformer-based Encoder-Decoder Models
• Article: Understanding BigBird's Block Sparse Attention"
• Article: Interactive Topic Modeling with BERTopic
• Article: Understanding Climate Change Domains through Topic Modeling
• Article: When Topic Modeling is Part of the Text Pre-processing
• Article: Keyword Extraction with BERT
• Article: Topic Modeling with BERT
• Article: Question Classification using Self-Attention Transformer — Part 1.1
• Article: Question Classification using Self-Attention Transformer — Part 1
• Article: Question Classification using Self-Attention Transformer — Part 2
• Article: Question Classification using Self-Attention Transformer — Part 3
• Article: Generalized Language Models
• Article: Learning Word Embedding
• Article: Reducing Toxicity in Language Models
• Article: The Transformer Family
• Article: DialogRPT with Huggingface Transformers
• Article: Hugging Face Reads - 01/2021 - Sparsity and Pruning
• Article: Hugging Face Reads, Feb. 2021 - Long-range Transformers
• Article: Porting fairseq wmt19 translation system to transformers
• Article: On word embeddings - Part 1
• Article: On word embeddings - Part 2: Approximating the Softmax
• Article: On word embeddings - Part 3: The secret ingredients of word2vec
• Article: Word embeddings in 2017: Trends and future direction
• Article: DaCy: New Fast and Efficient State-of-the-Art in Danish NLP!
• Article: State-of-the-Art Language Models in 2020
• Article: ML and NLP Publications in 2020
• Article: Zero-Shot Learning in Modern NLP
• Article: Introduction to recurrent neural networks
• Article: Understanding LSTM Networks
• Article: Explaining RNNs without neural networks
• Article: Understanding Convolutional Neural Networks for NLP
• Article: Search (Pt 1) — A Gentle Introduction
• Article: Search (Pt 2) — A Semantic Horse Race
• Article: Search (Pt 3) — Elastic Transformers
• Article: Improved Few-Shot Text classification
• Article: Text classification from few training examples
• Article: Multi-Label Text Classification
• Article: Semantic search using BERT embeddings
• Article: What Semantic Search Can do for You
• Article: How To Create Natural Language Semantic Search For Arbitrary Objects With Deep Learning
• Article: How to Implement a Beam Search Decoder for Natural Language Processing
• Article: Creating a class-based TF-IDF with Scikit-Learn
• Article: String Matching with BERT, TF-IDF, and more!
• Article: How to Use n-gram Models to Detect Format Errors in Datasets
• Article: The Unreasonable Effectiveness of Recurrent Neural Networks
• Article: A review of BERT based models
• Article: Document clustering
• Article: Document search with fragment embeddings
• Doc: Huggingface Summary of the models
• Doc: Summary of the tokenizers
• Article: GPT-2 A nascent transfer learning method that could eliminate supervised learning in some NLP tasks
• Article: Evaluation Metrics for Language Modeling
• Article: Representation Learning and Retrieval
• Article: A survey of cross-lingual word embedding models
• Article: Unsupervised Cross-lingual Representation Learning
• Article: Spelling Correction: How to make an accurate and fast corrector
• Article: Speller100: Zero-shot spelling correction at scale for 100-plus languages
• Article: Understanding BERT’s Semantic Interpretations
• Article: Using NLP (BERT) to improve OCR accuracy
• Article: Brief review of word embedding families (2019)
• Article: Trends in input representation for state-of-art NLP models (2019)
• Article: An Overview of Multi-Task Learning in Deep Neural Networks
• Article: Multi-Task Learning Objectives for Natural Language Processing
• Article: GPU Benchmarks for Fine-Tuning BERT
• Article: Recent Advances in Language Model Fine-tuning
• Article: The Current Best of Universal Word Embeddings and Sentence Embeddings
• Article: Topic Modeling for Keyword Extraction
• Article: Understanding ARPA and Language Models
• Article: Gaussian Mixture Models for Clustering
• Article: Explain NLP models with LIME & SHAP
• Article: How to solve 90% of NLP problems: a step-by-step guide
• Article: Does GPT-2 Know Your Phone Number?
• Article: How to Outperform GPT-3 by Combining Task Descriptions With Supervised Learning
• Article: LSTM Primer With Real Life Application( DeepMind Kidney Injury Prediction )*
• Article: T5 — XLNet — a clever language modeling solution
• Article: Using an NLP Q&A System To Study Climate Hazards and Nature-Based Solutions
• Article: Hyperparameter Optimization for 🤗Transformers: A guide
• Article: How To Do Things With Words. And Counters
• Article: Automatically Summarize Trump’s State of the Union Address
• Article: Solving NER with BERT for any entity type with very little training data (compared to past approaches)
• Article: 10 Things You Need to Know About BERT and the Transformer Architecture That Are Reshaping the AI Landscape
• Article: Semantic Entailment
• Article: Shrinking fastText embeddings so that it fits Google Colab
• Article: Fuzzy Matching/Fuzzy Logic Explained
• Article: Under the Hood of RNNs
• Article: All Our N-gram are Belong to You
• Article: Perplexity Intuition (and its derivation)
• Article: Part of Speech Tagging with Hidden Markov Chain Models
• Article: NLP Year In Review
• Article: UNDERSTANDING WORD2VEC THROUGH CULTURAL DIMENSIONS
• Article: Exploring LSTMs
• Article: Aspect-Based Opinion Mining (NLP with Python)
• Article: pyLDAvis: Topic Modelling Exploration Tool That Every NLP Data Scientist Should Know
• Article: ML and NLP Research Highlights of 2020
• Article: Introducing spaCy
• Article: 3 subword algorithms help to improve your NLP model performance
• Article: Examining BERT’s raw embeddings
• Article: Making sense of LSTMs by example
• Article: The Transformer Explained
• Article: Understanding building blocks of ULMFIT
• Article: Building a sentence embedding index with fastText and BM25
• Article: The Annotated GPT-2
• Article: Key topics extraction and contextual sentiment of users reviews
• Article: Google mT5 multilingual text-to-text transformer: A Brief Paper Analysis
• Article: Building RNNs is Fun with PyTorch and Google Colab
• Article: Faster and smaller quantized NLP with Hugging Face and ONNX Runtime
• Article: Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention)
• Article: How I Used Deep Learning To Train A Chatbot To Talk Like Me (Sorta)
• Article: Generating Questions Using Transformers
• Article: Feature-based Approach with BERT
• Article: Performers: The Kernel Trick, Random Fourier Features, and Attention
• Article: Text Similarities : Estimate the degree of similarity between two texts
• Article: NLP's ImageNet moment has arrived
• Article: Simple PyTorch Transformer Example with Greedy Decoding
• Article: Character level language model RNN
• Article: How we used Universal Sentence Encoder and FAISS to make our search 10x smarter
• Article: Adapting Text Augmentation to Industry problems
• Article: The Annotated Transformer
• Article: OpenAI's GPT-3 Language Model: A Technical Overview
• Article: NLP for Supervised Learning - A Brief Survey
• Article: The 4 Biggest Open Problems in NLP
• Article: How GPT3 Works
• Article: Why You Should Do NLP Beyond English
• Article: Breaking the spell of the spelling check
• Article: How to Write a Spelling Corrector
• Article: Spellchecking by computer
• Article: A Spellchecker Used to Be a Major Feat of Software Engineering
• Article: 1000x Faster Spelling Correction algorithm (2012)
• Article: The Pruning Radix Trie — a Radix Trie on steroids
• Article: Text Data Cleanup - Dynamic Embedding Visualisation
• Article: Rotary Embeddings: A Relative Revolution
• Article: Using embeddings to help find similar restaurants in Search
• Article: Evolution of and experiments with feed ranking at Swiggy
• Article: Personalizing Swiggy POP Recommendations
• Article: Fan(s)tastic: Search for blazing-fast results
• Article: Find My Food: Semantic Embeddings for Food Search Using Siamese Networks
• Article: Learning To Rank Restaurants
• Article: Is Word Sense Disambiguation outdated?
• Article: Named-Entity evaluation metrics based on entity-level
• Article: Comparison Of Ngram Fuzzy Matching Approaches
• Article: String similarity — the basic know your algorithms guide!
• Article: Evolution of Word to Vector
• Article: Unsupervised Auto-labeling of Websites
• Article: A friendly introduction to Recurrent Neural Networks
• Article: Introducing Translatotron: An End-to-End Speech-to-Speech Translation Model
• Book: Embeddings in Natural Language Processing
• Book: Linguistic Fundamentals for Natural Language Processing: 100 Essentials from Morphology and Syntax
• Coursera: Sequence Models
• Coursera: Natural Language Processing in TensorFlow
• CMU: Low-resource NLP Bootcamp 2020
  • CMU Low resource NLP Bootcamp 2020 (1): NLP Tasks 1:46:06
  • CMU Low resource NLP Bootcamp 2020 (2): Linguistics - Phonology and Morphology 1:24:08
  • CMU Low resource NLP Bootcamp 2020 (3): Machine Translation 1:55:59
  • CMU Low resource NLP Bootcamp 2020 (4): Linguistics - Syntax and Morphosyntax 2:00:21
  • CMU Low resource NLP Bootcamp 2020 (5): Neural Representation Learning 1:19:57
  • CMU Low resource NLP Bootcamp 2020 (6): Multilingual NLP 2:04:34
  • CMU Low resource NLP Bootcamp 2020 (7): Speech Synthesis 2:22:14
• CMU: Neural Nets for NLP 2021
  • CMU Neural Nets for NLP 2021 (1): Introduction 1:22:40
  • CMU Neural Nets for NLP 2021 (2): Language Modeling, Efficiency/Training Tricks 0:58:24
  • CMU Neural Nets for NLP 2021 (3): Building A Neural Network Toolkit for NLP, minnn 0:34:42
  • CMU Neural Nets for NLP 2021 (4): Efficiency Tricks for Neural Nets 0:43:28
  • CMU Neural Nets for NLP 2021 (5): Recurrent Neural Networks 0:38:50
  • CMU Neural Nets for NLP 2021 (6): Conditioned Generation 0:45:06
  • CMU Neural Nets for NLP 2021 (7): Attention 0:38:23
  • CMU Neural Nets for NLP 2021 (8): Distributional Semantics and Word Vectors 0:42:44
  • CMU Neural Nets for NLP 2021 (9): Sentence and Contextual Word Representations 0:50:53
  • CMU Neural Nets for NLP 2021 (11): Structured Prediction with Local Independence Assumptions 0:36:43
  • CMU Neural Nets for NLP 2021 (10): Debugging Neural Nets (for NLP) 0:43:58
  • CMU Neural Nets for NLP 2021 (12): Model Interpretation 0:28:52
  • CMU Neural Nets for NLP 2021 (13): Generating Trees and Graphs 0:41:05
  • CMU Neural Nets for NLP 2021 (14): Margin-based and Reinforcement Learning for Structured Prediction 0:47:20
  • CMU Neural Nets for NLP 2021 (15): Sequence-to-sequence Pre-training 0:27:22
  • CMU Neural Nets for NLP 2021 (16): Machine Reading w/ Neural Nets 0:43:08
  • CMU Neural Nets for NLP 2021 (17): Neural Nets + Knowledge Bases 0:44:19
  • CMU Neural Nets for NLP 2021 (18): Advanced Search Algorithms 0:47:58
  • CMU Neural Nets for NLP 2021 (19): Adversarial Methods 0:41:56
  • CMU Neural Nets for NLP 2021 (20): Models w/ Latent Random Variables 0:41:06
  • CMU Neural Nets for NLP 2021 (21): Multilingual Learning 0:33:10
  • CMU Neural Nets for NLP 2021 (22): Bias in NLP 0:32:44
  • CMU Neural Nets for NLP 2021 (23): Document-level Models 0:40:04
• CMU Multilingual NLP 2020
  • CMU Multilingual NLP 2020 (1): Introduction 1:17:29
  • CMU Multilingual NLP 2020 (2): Typology - The Space of Language 0:37:13
  • CMU Multilingual NLP 2020 (3): Words, Parts of Speech, Morphology 0:38:58
  • CMU Multilingual NLP 2020 (4): Text Classification and Sequence Labeling 0:45:56
  • CMU Multilingual NLP 2020 (5): Advanced Text Classification/Labeling 0:49:40
  • CMU Multilingual NLP 2020 (6): Translation, Evaluation, and Datasets 0:46:17
  • CMU Multilingual NLP 2020 (7): Machine Translation/Sequence-to-sequence Models 0:43:51
  • CMU Multilingual NLP 2020 (8): Data Augmentation for Machine Translation 0:24:42
  • CMU Multilingual NLP 2020 (9): Language Contact and Similarity Across Languages 0:30:25
  • CMU Multilingual NLP 2020 (10): Multilingual Training and Cross-lingual Transfer 0:39:58
  • CMU Multilingual NLP 2020 (11): Unsupervised Translation 0:51:17
  • CMU Multilingual NLP 2020 (12): Code Switching, Pidgins, and Creoles 0:46:37
  • CMU Multilingual NLP 2020 (13): Speech 0:41:16
  • CMU Multilingual NLP 2020 (14): Automatic Speech Recognition 0:39:33
  • CMU Multilingual NLP 2020 (15): Low Resource ASR 0:43:38
  • CMU Multilingual NLP 2020 (16): Text to Speech 0:39:00
  • CMU Multilingual NLP 2020 (17): Morphological Analysis and Inflection 0:45:22
  • CMU Multilingual NLP 2020 (18): Dependency Parsing 0:38:15
  • CMU Multilingual NLP 2020 (19): Data Annotation 0:53:08
  • CMU Multilingual NLP 2020 (20): Active Learning 0:28:37
  • CMU Multilingual NLP 2020 (21): Information Extraction 0:41:00
  • CMU Multilingual NLP 2020 (22): Multilingual NLP for Indigenous Languages 1:21:58
  • CMU Multilingual NLP 2020 (23): Universal Translation at Scale 1:27:33
• CMU Advanced NLP 2021
  • CMU Advanced NLP 2021 (1): Introduction to NLP 1:08:39
  • CMU Advanced NLP 2021 (2): Text Classification 1:16:56
  • CMU Advanced NLP 2021 (3): Language Modeling and Neural Networks 1:16:37
  • CMU Advanced NLP 2021 (4): Text Classification 1:14:19
  • CMU Advanced NLP 2021 (5): Recurrent Neural Networks 1:13:43
  • CMU Advanced NLP 2021 (6): Conditional Generation 1:17:56
• CS685: Advanced Natural Language Processing
  • UMass CS685 (Advanced NLP): Attention mechanisms 0:48:53
  • UMass CS685 (Advanced NLP): Question answering 0:59:50
  • UMass CS685 (Advanced NLP): Better BERTs 0:52:23
  • UMass CS685 (Advanced NLP): Text generation decoding and evaluation 1:02:32
  • UMass CS685 (Advanced NLP): Paraphrase generation 1:10:59
  • UMass CS685 (Advanced NLP): Crowdsourced text data collection 0:58:31
  • UMass CS685 (Advanced NLP): Model distillation and security threats 1:09:25
  • UMass CS685 (Advanced NLP): Retrieval-augmented language models 0:52:13
  • UMass CS685 (Advanced NLP): Implementing a Transformer 1:12:36
  • UMass CS685 (Advanced NLP): vision + language 1:06:28
  • UMass CS685 (Advanced NLP): exam review 1:24:36
  • UMass CS685 (Advanced NLP): Intermediate fine-tuning 1:10:35
  • UMass CS685 (Advanced NLP): ethics in NLP 0:56:57
  • UMass CS685 (Advanced NLP): probe tasks 0:54:30
  • UMass CS685 (Advanced NLP): semantic parsing 0:48:49
  • UMass CS685 (Advanced NLP): commonsense reasoning (guest lecture by Lorraine Li) 0:58:53
• Datacamp: Advanced NLP with spaCy
• Datacamp: Building Chatbots in Python
• Datacamp: Clustering Methods with SciPy
• Datacamp: Feature Engineering for NLP in Python
• Datacamp: Machine Translation in Python
• Datacamp: Natural Language Processing Fundamentals in Python
• Datacamp: Natural Language Generation in Python
• Datacamp: RNN for Language Modeling
• Datacamp: Regular Expressions in Python
• Datacamp: Sentiment Analysis in Python
• Datacamp: Spoken Language Processing in Python
• Notebook: NNLM - Predict Next Word
• Notebook: Word2Vec
• Notebook: FastText Sentence Classification
• Notebook: TextCNN - Binary Sentiment Classification
• Notebook: TextRNN - Predict Next Step
• Notebook: TextLSTM - Autocomplete
• Notebook: Bi-LSTM - Predict Next Word in Long Sentence
• Notebook: SeqSeq - Change Word
• Notebook: Seq2Seq with Attention - Translate
• Notebook: Bi-LSTM with Attention - Binary Sentiment Classification
• Notebook: The Transformer - Translate
• Notebook: The Transformer - Greedy Decoder
• Notebook: BERT - NSP and MLM
• Notebook: Logistic regression-Tf-Idf baseline
• RNN and LSTM
• Spacy Tutorial
• Stanford CS224U: Natural Language Understanding | Spring 2019
  • Lecture 1 – Course Overview | Stanford CS224U: Natural Language Understanding | Spring 2019 1:12:59
  • Lecture 2 – Word Vectors 1 | Stanford CS224U: Natural Language Understanding | Spring 2019 1:17:10
  • Lecture 3 – Word Vectors 2 | Stanford CS224U: Natural Language Understanding | Spring 2019 1:16:52
  • Lecture 4 – Word Vectors 3 | Stanford CS224U: Natural Language Understanding | Spring 2019 0:38:20
  • Lecture 5 – Sentiment Analysis 1 | Stanford CS224U: Natural Language Understanding | Spring 2019 1:10:44
  • Lecture 6 – Sentiment Analysis 2 | Stanford CS224U: Natural Language Understanding | Spring 2019 1:03:23
  • Lecture 7 – Relation Extraction | Stanford CS224U: Natural Language Understanding | Spring 2019 1:19:04
  • Lecture 8 – NLI 1 | Stanford CS224U: Natural Language Understanding | Spring 2019 1:15:02
  • Lecture 9 – NLI 2 | Stanford CS224U: Natural Language Understanding | Spring 2019 1:15:35
  • Lecture 10 – Grounding | Stanford CS224U: Natural Language Understanding | Spring 2019 1:23:15
  • Lecture 11 – Semantic Parsing | Stanford CS224U: Natural Language Understanding | Spring 2019 1:07:05
  • Lecture 12 – Evaluation Methods | Stanford CS224U: Natural Language Understanding | Spring 2019 1:18:32
  • Lecture 13 – Evaluation Metrics | Stanford CS224U: Natural Language Understanding | Spring 2019 1:11:32
  • Lecture 14 – Contextual Vectors | Stanford CS224U: Natural Language Understanding | Spring 2019 1:14:33
  • Lecture 15 – Presenting Your Work | Stanford CS224U: Natural Language Understanding | Spring 2019 1:15:11
• Stanford CS224N: Stanford CS224N: NLP with Deep Learning | Winter 2019
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 1 – Introduction and Word Vectors 1:21:52
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 2 – Word Vectors and Word Senses 1:20:43
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 3 – Neural Networks 1:18:50
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 4 – Backpropagation 1:22:15
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 5 – Dependency Parsing 1:20:22
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 6 – Language Models and RNNs 1:08:25
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 7 – Vanishing Gradients, Fancy RNNs 1:13:23
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 8 – Translation, Seq2Seq, Attention 1:16:56
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 9 – Practical Tips for Projects 1:22:39
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 10 – Question Answering 1:21:01
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 11 – Convolutional Networks for NLP 1:20:18
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 12 – Subword Models 1:15:30
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 13 – Contextual Word Embeddings 1:20:18
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 14 – Transformers and Self-Attention 0:53:48
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 15 – Natural Language Generation 1:19:37
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 16 – Coreference Resolution 1:19:20
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 17 – Multitask Learning 1:11:54
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 18 – Constituency Parsing, TreeRNNs 1:20:37
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 19 – Bias in AI 0:56:03
  • Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 20 – Future of NLP + Deep Learning 1:19:15
  • Stanford CS224N: NLP with Deep Learning | Winter 2020 | Low Resource Machine Translation 1:15:45
  • Stanford CS224N: NLP with Deep Learning | Winter 2020 | BERT and Other Pre-trained Language Models 0:54:28
• Stanford: CS214 From Languages to Information
  • 1 1 Regular Expressions 11 25 0:11:25
  • 1 2 Regular Expression Substitutions 0:06:10
  • 1 3 Words and Corpora 0:06:25
  • 1 4 Word Tokenization 0:08:21
  • 1 5 Byte Pair Encoding 0:07:38
  • 1 6 Word Normalization 0:06:23
  • 2 1 Defining Minimum Edit Distance 7 04 0:07:05
  • 2 2 Computing Minimum Edit Distance 5 54 0:05:55
  • 2 3 Backtrace for Computing Alignments 5 55 0:05:56
  • 2 4 Weighted Minimum Edit Distance 2 47 0:02:48
  • 2 5 Minimum Edit Distance in Computational Biology 9 29 0:09:30
  • 3 1 Introduction to N grams 8 41 0:08:41
  • 3 2 Estimating N gram Probabilities 9 38 0:09:38
  • 3 3 Evaluation and Perplexity 0:12:37
  • 3 4 Generalization and Zeros 5 15 0:05:15
  • 3 5 Smoothing Add One 6 30 0:06:31
  • 3 6 Interpolation 10 25 0:10:25
  • 3 8 Kneser Ney Smoothing 8 59 0:08:59
  • 5 1 What is Text Classification 8 12 0:08:12
  • Naive Bayes Lecture 2 The Naive Bayes Classifier 0:12:24
  • Naive Bayes 3 Learning in Naive Bayes 0:06:04
  • Naive Bayes 4 Sentiment and Binary NB 0:08:14
  • 4 5 More on Sentiment Classification 0:05:14
  • 5 2 Naive Bayes Relationship to Language Modeling 4 35 0:04:36
  • 5 7 Precision, Recall, and the F measure 16 16 0:16:17
  • 5 8 Text Classification Evaluation 7 17 0:07:17
  • Logistic Regression 1 Generative and Discriminative Classifiers 0:05:25
  • Logistic Regression 2 Classification 0:07:48
  • Logistic Regression 3 A Sentiment Example 0:05:09
  • Logistic Regression 4 Cross Entropy Loss 0:07:59
  • Logistic Regression 5 Stochastic Gradient Descent 0:09:46
  • Logistic Regression 6 A worked example of gradient descent 0:05:10
  • 7 1 Introduction to Information Retrieval 9 16 0:09:16
  • 7 2 Term Document Incidence Matrices 8 59 0:08:59
  • 7 3 The Inverted Index 10 42 0:10:43
  • 7 4 Query Processing with the Inverted Index 6 43 0:06:44
  • 7 5 The Boolean Retrieval Model 14 06 0:14:07
  • 7 6 Phrase Queries and Positional Indexes 19 45 0:19:46
  • 8 1 Introducing Ranked Retrieval 4 27 0:04:27
  • 8 2 Scoring with the Jaccard Coefficient 5 06 0:05:07
  • 8 3 Term Frequency Weighting 5 59 0:06:00
  • 8 4 Inverse Document Frequency Weighting 10 16 0:10:17
  • 8 5 TF IDF Weighting 3 42 0:03:42
  • 8 6 The Vector Space Model 16 22 0:16:23
  • 8 7 Calculating TF IDF Cosine Scores 12 47 0:12:48
  • 8 8 Evaluating Search Engines 9 02 0:09:03
  • Introduction to Named Entity Tagging 0:05:06
  • Introduction to Part of Speech Tagging 0:09:03
  • Vector 1 Word Meaning 0:09:09
  • Vector 2 Vector Semantics 0:06:37
  • Vector 3 Words and Vectors 0:05:16
  • Vector 4 Cosine Similarity 0:04:23
  • Vector 5 TF IDF 0:05:32
  • Vector 6 Word2vec 0:07:39
  • Vector 7 Learning in Word2vec 0:07:36
  • Vector 8 Properties of Embeddings 0:06:08
  • Neural Networks 1 Neural Units 0:05:41
  • Neural Networks 2 XOR 0:07:32
  • Neural Networks 3 Feedforward Neural Networks 0:08:55
  • Neural Networks 4 Applying Feedforward Networks to NLP 0:07:15
  • Neural Networks 5 Overview of Training 0:04:21
  • Neural Networks 6 Computation Graphs and Backward Differentiation 0:10:31
  • Dialog 1 Overview 0:03:11
  • Dialogue 2 Human Conversation 0:10:31
  • Dialogue 3 ELIZA 0:09:27
  • Dialogue 4 Corpus Chatbots 0:09:35
  • Dialogue 5 Frame Based Dialogue 0:07:41
  • Dialogue 6 Dialogue State Architecture 0:08:58
  • Dialogue 7 Dialogue State Architecture Policy and Generation 0:08:23
  • Dialogue 8 Evaluation 0:04:38
  • Dialogue 9 Design and Ethical Issues 0:03:29
  • Recommender Systems 1 Introduction 0:06:02
  • Recommender Systems 2 Content Based 0:05:50
  • Recommender Systems 3 User User Collaborative Filtering 0:07:50
  • Recommender Systems 4 Item Item Collaborative Filtering 0:06:52
  • Recommender Systems 5 Simplified version for PA6 0:02:10
  • 14 1 Anchor Text 3 39 0:03:40
  • 14 2 PageRank Overview and Markov Chains 12 10 0:12:10
  • 14 3 Computing PageRank 8 09 0:08:10
  • Social Networks 1 Networks 0:06:58
• TextBlob Tutorial Series
  • Natural Language Processing Tutorial With TextBlob -Tokens,Translation and Ngrams 0:11:01
  • NLP Tutorial With TextBlob and Python - Parts of Speech Tagging 0:05:59
  • NLP Tutorial With TextBlob & Python - Lemmatizating 0:06:32
  • NLP Tutorial with TextBlob & Python - Sentiment Analysis(Polarity,Subjectivity) 0:06:31
  • Building a NLP-based Flask App with TextBlob 0:37:30
  • Natural Language Processing with Polyglot - Installation & Intro 0:12:49
• Youtube: fast.ai Code-First Intro to Natural Language Processing
  • What is NLP? (NLP video 1) 0:22:42
  • Topic Modeling with SVD & NMF (NLP video 2) 1:06:39
  • Topic Modeling & SVD revisited (NLP video 3) 0:33:05
  • Sentiment Classification with Naive Bayes (NLP video 4) 0:58:20
  • Sentiment Classification with Naive Bayes & Logistic Regression, contd. (NLP video 5) 0:51:29
  • Derivation of Naive Bayes & Numerical Stability (NLP video 6) 0:23:56
  • Revisiting Naive Bayes, and Regex (NLP video 7) 0:37:33
  • Intro to Language Modeling (NLP video 8) 0:40:58
  • Transfer learning (NLP video 9) 1:35:16
  • ULMFit for non-English Languages (NLP Video 10) 1:49:22
  • Understanding RNNs (NLP video 11) 0:33:16
  • Seq2Seq Translation (NLP video 12) 0:59:42
  • Word embeddings quantify 100 years of gender & ethnic stereotypes-- Nikhil Garg (NLP video 13) 0:47:17
  • Text generation algorithms (NLP video 14) 0:25:39
  • Implementing a GRU (NLP video 15) 0:23:13
  • Algorithmic Bias (NLP video 16) 1:26:17
  • Introduction to the Transformer (NLP video 17) 0:22:54
  • The Transformer for language translation (NLP video 18) 0:55:17
  • What you need to know about Disinformation (NLP video 19) 0:51:21
  • Article: Zero to Hero with fastai - Beginner
  • Article: Zero to Hero with fastai - Intermediate
• NLP Course | For You
  • Word Embeddings
  • Text Classification
  • Language Modeling
  • Seq2seq and Attention
• Youtube: BERT Research Series
• YouTube: Intro to NLP with Spacy
• Talk: Practical NLP for the Real World
• YouTube: Level 3 AI Assistant Conference 2020
  • Youtube: Conversation Analysis Theory in Chatbots | Michael Szul
  • Youtube: Designing Practical NLP Solutions | Ines Montani
  • Youtube: Effective Copywriting for Chatbots | Hans Van Dam
  • Youtube: Distilling BERT | Sam Sucik
  • Youtube: Transformer Policies that improve Dialogues: A Live Demo by Vincent Warmerdam
  • Youtube: From Research to Production – Our Process at Rasa | Tanja Bunk
  • Youtube: Keynote: Perspective on the 5 Levels of Conversational AI | Alan Nichol
• Youtube: RASA Algorithm Whiteboard
  • Introducing The Algorithm Whiteboard 0:01:16
  • Rasa Algorithm Whiteboard - Diet Architecture 1: How it Works 0:23:27
  • Rasa Algorithm Whiteboard - Diet Architecture 2: Design Decisions 0:15:06
  • Rasa Algorithm Whiteboard - Diet Architecture 3: Benchmarking 0:22:34
  • Rasa Algorithm Whiteboard - Embeddings 1: Just Letters 0:13:48
  • Rasa Algorithm Whiteboard - Embeddings 2: CBOW and Skip Gram 0:19:24
  • Rasa Algorithm Whiteboard - Embeddings 3: GloVe 0:19:12
  • Rasa Algorithm Whiteboard - Embeddings 4: Whatlies 0:14:03
  • Rasa Algorithm Whiteboard - Attention 1: Self Attention 0:14:32
  • Rasa Algorithm Whiteboard - Attention 2: Keys, Values, Queries 0:12:26
  • Rasa Algorithm Whiteboard - Attention 3: Multi Head Attention 0:10:55
  • Rasa Algorithm Whiteboard: Attention 4 - Transformers 0:14:34
  • Rasa Algorithm Whiteboard - StarSpace 0:11:46
  • Rasa Algorithm Whiteboard - TED Policy 0:16:10
  • Rasa Algorithm Whiteboard - TED in Practice 0:14:54
  • Rasa Algorithm Whiteboard - Response Selection 0:12:07
  • Rasa Algorithm Whiteboard - Response Selection: Implementation 0:09:25
  • Rasa Algorithm Whiteboard - Countvectors 0:13:32
  • Rasa Algorithm Whiteboard - Subword Embeddings 0:11:58
  • Rasa Algorithm Whiteboard - Implementation of Subword Embeddings 0:10:01
  • Rasa Algorithm Whiteboard - BytePair Embeddings 0:12:44
• Youtube: A brief history of the Transformer architecture in NLP
• Youtube: The Transformer neural network architecture explained. “Attention is all you need” (NLP)
• Youtube: How does a Transformer architecture combine Vision and Language? ViLBERT - NLP meets Computer Vision
• Youtube: Strategies for pre-training the BERT-based Transformer architecture – language (and vision)
• Youtube: Ilya Sutskever - GPT-2
• Youtube: NLP Masterclass | Modeling Fallacies in NLP
• Youtube: What is GPT-3? Showcase, possibilities, and implications
• Youtube: TextAttack: A Framework for Data Augmentation and Adversarial Training in NLP
• Article: How the Embedding Layers in BERT Were Implemented
• Youtube: Easy Data Augmentation for Text Classification
• Youtube: Webinar: Special NLP Session with Hugging Face
• Youtube: Spacy IRL 2019
  • Sebastian Ruder: Transfer Learning in Open-Source Natural Language Processing (spaCy IRL 2019) 0:31:24
  • Giannis Daras: Improving sparse transformer models for efficient self-attention (spaCy IRL 2019) 0:20:13
  • Peter Baumgartner: Applied NLP: Lessons from the Field (spaCy IRL 2019) 0:18:44
  • Justina Petraitytė: Lessons learned in helping ship conversational AI assistants (spaCy IRL 2019) 0:23:48
  • Yoav Goldberg: The missing elements in NLP (spaCy IRL 2019) 0:30:27
  • Sofie Van Landeghem: Entity linking functionality in spaCy (spaCy IRL 2019) 0:20:08
  • Guadalupe Romero: Rethinking rule-based lemmatization (spaCy IRL 2019) 0:14:49
  • Mark Neumann: ScispaCy: A spaCy pipeline & models for scientific & biomedical text (spaCy IRL 2019) 0:18:59
  • Patrick Harrison: Financial NLP at S&P Global (spaCy IRL 2019) 0:21:42
  • McKenzie Marshall: NLP in Asset Management (spaCy IRL 2019) 0:20:32
  • David Dodson: spaCy in the News: Quartz's NLP pipeline (spaCy IRL 2019) 0:20:56
  • Matthew Honnibal & Ines Montani: spaCy and Explosion: past, present & future (spaCy IRL 2019) 0:54:13
• Youtube: The Future of Natural Language Processing
• Youtube: Sentiment Analysis: Key Milestones, Challenges and New Directions
• Youtube: Simple and Efficient Deep Learning for Natural Language Processing, with Moshe Wasserblat, Intel AI
• Youtube: Why not solve biological problems with a Transformer? BERTology meets Biology
• Youtube: Self-attention step-by-step | How to get meaning from text
• Youtube: Chat Bot with PyTorch
• Youtube: NLP with Friends Talks
  • NLP with Friends, Featured Friend: Tom McCoy 0:36:48
  • NLP with Friends, Featured Friend: Maarten Sap 0:36:11
  • NLP with Friends, featured friend: Nitika Mathur 1:01:42
  • NLP with Friends, Featured Friend: Sabrina J Mielke 1:01:28
• Youtube: Insincere Question Classification with PyTorch
  • [PART 1] Insincere Question Classification with PyTorch 0:22:34
  • [PART 2] Insincere Question Classification with PyTorch 0:33:53
  • [PART 3] Insincere Question Classification with PyTorch 0:23:49
  • [PART 4] Insincere Question Classification with PyTorch 0:14:25
• Crash Course: Linguistics
  • Crash Course Linguistics Preview 0:02:50
  • What is Linguistics?: Crash Course Linguistics #1 0:11:11
• Youtube: Recent Advances in Language Pretraining and Generation
• Youtube: Talks # 3: Lorenzo Ampil - Introduction to T5 for Sentiment Span Extraction
• Youtube: Frontiers in ML: Learning from Limited Labeled Data: Challenges and Opportunities for NLP
• Youtube: DeepLearning.ai NLP talk: Chris Manning
• Youtube: DeepLearning.ai NLP talk: Oren Etzioni
• Youtube: DeepLearning.ai NLP talk: Quoc Le
• Youtube: What can MIR learn from transfer learning in NLP?
• Youtube: The Narrated Transformer Language Model
• Youtube: spaCy v3.0: Bringing State-of-the-art NLP from Prototype to Production 00:22:40
• Youtube: Conversational AI with Transformers and Rule-Based Systems 1:53:24
• Talk: High Performance Natural Language Processing
• Talk: EmoTag1200: Understanding the Association between Emojis and Emotions
• Youtube: Research Paper Walkthrough
  • Simple Unsupervised Keyphrase Extraction using Sentence Embeddings | Research Paper Walkthrough 0:21:23
  • Leveraging BERT for Extractive Text Summarization on Lectures | Research Paper Walkthrough 0:20:10
  • Data Augmentation Techniques for Text Classification in NLP | Research Paper Walkthrough 0:14:33
  • CRIM at SemEval-2018 Task 9: A Hybrid Approach to Hypernym Discovery | Research Paper Walkthrough 0:23:47
  • Data Augmentation using Pre-trained Transformer Model (BERT, GPT2, etc) | Research Paper Walkthrough 0:17:43
  • A Supervised Approach to Extractive Summarisation of Scientific Papers | Research Paper Walkthrough 0:19:01
  • BLEURT: Learning Robust Metrics for Text Generation | Research Paper Walkthrough 0:13:38
  • DeepWalk: Online Learning of Social Representations | ML with Graphs | Research Paper Walkthrough 0:17:44
  • LSBert: A Simple Framework for Lexical Simplification | Research Paper Walkthrough 0:20:27
  • SpanBERT: Improving Pre-training by Representing and Predicting Spans | Research Paper Walkthrough 0:14:21
  • Text Summarization of COVID-19 Medical Articles using BERT and GPT-2 | Research Paper Walkthrough 0:21:52
  • Extractive & Abstractive Summarization with Transformer Language Models | Research Paper Walkthrough 0:16:58
  • Unsupervised Multi-Document Summarization using Neural Document Model | Research Paper Walkthrough 0:15:11
  • SummPip: Multi-Document Summarization with Sentence Graph Compression | Research Paper Walkthrough 0:16:54
  • Combining BERT with Static Word Embedding for Categorizing Social Media | Research Paper Walkthrough 0:13:51
  • Reformulating Unsupervised Style Transfer as Paraphrase Generation | Research Paper Walkthrough 0:19:41
  • PEGASUS: Pre-training with Gap-Sentences for Abstractive Summarization | Research Paper Walkthrough 0:15:04
  • Evaluation of Text Generation: A Survey | Human-Centric Evaluations | Research Paper Walkthrough 0:15:54
  • TOD-BERT: Pre-trained Transformers for Task-Oriented Dialogue Systems (Research Paper Walkthrough) 0:15:25
  • TextRank: Bringing Order into Texts (Research Paper Walkthrough) 0:14:34
  • Node2Vec: Scalable Feature Learning for Networks | ML with Graphs (Research Paper Walkthrough) 0:14:33
  • HARP: Hierarchical Representation Learning for Network | ML with Graphs (Research Paper Walkthrough) 0:15:10
  • URL2Video: Automatic Video Creation From a Web Page | AI and Creativity (Research Paper Walkthrough) 0:15:21
  • On Generating Extended Summaries of Long Documents (Research Paper Walkthrough) 0:14:24
  • Nucleus Sampling: The Curious Case of Neural Text Degeneration (Research Paper Walkthrough) 0:12:48
  • T5: Exploring Limits of Transfer Learning with Text-to-Text Transformer (Research Paper Walkthrough) 0:12:47
  • DialoGPT: Generative Training for Conversational Response Generation (Research Paper Walkthrough) 0:13:17
  • Hierarchical Transformers for Long Document Classification (Research Paper Walkthrough) 0:12:46
  • Beyond Accuracy: Behavioral Testing of NLP Models with CheckList (Best Paper ACL 2020) 0:14:00
• NLP Summit 2020
  • The 2020 Trends for Applied Natural Language Processing | NLP Summit 2020 0:21:10
  • NLP Industry Survey Analysis: the landscape of natural language use cases in 2020 | NLP Summit 2020 0:20:23
  • Auto NLP: Pretrain, Tune & Deploy State-of-the-art Models Without Coding 0:19:57
  • Proof-of-Concept Delight | NLP Summit 2020 0:16:50
  • Distributed Natural Language Processing Apps for Financial Engineering | NLP Summit 2020 0:34:49
  • Bleeding Edge Applications of 2020 Transformers | NLP Summit 2020 0:33:34
  • How Freshworks Freddy AI leverages NLP for Ethics-First Customer Experiences | NLP Summit 2020 0:26:49
  • NLP for Recruitment Automation: Building a Chatbot from the Job Description | NLP Summit 2020 0:22:31
• Youtube: Explainability for Natural Language Processing
• Youtube: Gibberish Detector
• Youtube: NLP Lecture 7 Constituency Parsing
  • NLP Lecture 7 - Overview of Constituency Parsing Lecture 0:01:50
  • NLP Lecture 7 - Introduction to Constituency Parsing 0:10:29
  • NLP Lecture 7(a) - Context Free Grammar 0:17:03
  • NLP Lecture 7(b) - Constituency Parsing 0:13:28
  • NLP Lecture 7(c) - Statistical Constituency Parsing 0:09:38
  • NLP Lecture 7(d) - Dependency Parsing 0:17:15
• Youtube: LING 83 Teaching Video: Constituency Parsing
• Youtube: SpaCy for Digital Humanities with Python Tutorials
  • Introduction to SpaCy and Cleaning Data (SpaCy and Python Tutorials for DH - 01) 0:06:07
  • How to Install SpaCy and Models (Spacy and Python Tutorial for DH 02) 0:07:40
  • How to Separate Sentences in SpaCy (SpaCy and Python Tutorials for DH - 03) 0:08:33
  • Spacy and Named Entity Recognition NER (Spacy and Python Tutorial for DH 04) 0:08:32
  • Finding Parts of Speech (SpaCy and Python Tutorial for DH 05) 0:02:55
  • Extracting Nouns and Noun Chunks (SpaCy and Python Tutorial for DH 06) 0:05:46
  • Extracting Verbs and Verb Phrases (SpaCy and Python Tutorial for DH 07) 0:08:10
  • Lemmatization: Finding the Roots of Words (Spacy and Python Tutorial for DH 08) 0:04:52
  • Data Visualization with DisplaCy (Spacy and Python Tutorial for DH 09) 0:09:13
  • Customizing DisplaCy Render Data Visualization (Spacy and Python Tutorial for DH 10) 0:08:19
  • Finding Quotes in Sentences (SpaCy and Python Tutorial for DH 11) 0:08:45
  • Introduction to Named Entity Recognition (NER for DH 01) 0:16:43
  • Machine Learning NER with Python and spaCy (NER for DH 03 ) 0:13:36
  • How to Use spaCy's EntityRuler (Named Entity Recognition for DH 04 | Part 01) 0:36:50
  • How to Use spaCy to Create an NER training set (Named Entity Recognition for DH 04 | Part 02) 0:10:32
  • How to Train a spaCy NER model (Named Entity Recognition for DH 04 | Part 03) 0:15:40
  • Examining a spaCy Model in the Folder (Named Entity Recognition for DH 05) 0:15:06
  • What are Word Vectors (Named Entity Recognition for DH 06) 0:18:49
  • How to Generate Custom Word Vectors in Gensim (Named Entity Recognition for DH 07) 0:23:05
  • How to Load Custom Word Vectors into spaCy Models (Named Entity Recognition for DH 08) 0:10:46
  • Getting the Data for Custom Labels (Holocaust NER for DH 09.01) 0:11:00
  • How to Add a Custom NER Pipe in spaCy and a Custom Label (NER for DH 09.02 ) 0:07:49
  • How to Training Custom Entities into spaCy Models (Named Entity Recognition for DH 09 03) 0:15:29
  • How to Add and Place Pipes from other Models into a New Model (NER for DH 09 04) 0:12:24
  • How to Add Custom Functions to spaCy Pipeline (NER for DH 09.05) 0:15:20
  • Precision vs. Recall and Adding PERSON to Holocaust NER Pipeline (Named Entity Recognition DH 09.06) 0:26:02
  • Finalizing the Holocaust NER Pipeline (Named Entity Recognition for DH 09.07) 0:14:16
  • Classical Latin Named Entity Recognition (NER for DH 10.01) 0:55:30
  • How to Package spaCy Models (Even with Custom Factories) (NER for DH 11) 0:15:31
• Youtube: Billion-scale Approximate Nearest Neighbor Search
• Youtube: Data Science - Fuzzy Record Matching
• Youtube: Minimum Edit Distance Dynamic Programming
• Youtube: Cheuk Ting Ho - Fuzzy Matching Smart Way of Finding Similar Names Using Fuzzywuzzy
• Youtube: What's in a Name? Fast Fuzzy String Matching - Seth Verrinder & Kyle Putnam - Midwest.io 2015
• Youtube: Jiaqi Liu Fuzzy Search Algorithms How and When to Use Them PyCon 2017
• Youtube: 1 + 1 = 1 or Record Deduplication with Python | Flávio Juvenal @ PyBay2018
• Youtube: Mike Mull: The Art and Science of Data Matching
• Youtube: Record linkage: Join for real life by Rhydwyn Mcguire
• Youtube: Approximate nearest neighbors and vector models, introduction to Annoy
• Youtube: Librosa Audio and Music Signal Analysis in Python | SciPy 2015 | Brian McFee
• Video: Recent Advances in LM Pre-training
• Youtube: Deep Learning (for Audio) with Python
  • 1- Deep Learning (for Audio) with Python: Course Overview 0:08:02
  • 2- AI, machine learning and deep learning 0:31:15
  • 3- Implementing an artificial neuron from scratch 0:19:05
  • 4- Vector and matrix operations 0:25:51
  • 5- Computation in neural networks 0:23:19
  • 6- Implementing a neural network from scratch in Python 0:21:03
  • 7- Training a neural network: Backward propagation and gradient descent 0:21:41
  • 8- TRAINING A NEURAL NETWORK: Implementing backpropagation and gradient descent from scratch 1:03:00
  • 9- How to implement a (simple) neural network with TensorFlow 2 0:24:37
  • 10 - Understanding audio data for deep learning 0:32:55
  • 11- Preprocessing audio data for Deep Learning 0:25:05
  • 12- Music genre classification: Preparing the dataset 0:37:45
  • 13- Implementing a neural network for music genre classification 0:33:25
  • 14- SOLVING OVERFITTING in neural networks 0:26:29
  • 15- Convolutional Neural Networks Explained Easily 0:35:23
  • 16- How to Implement a CNN for Music Genre Classification 0:49:10
  • 17- Recurrent Neural Networks Explained Easily 0:28:35
  • 18- Long Short Term Memory (LSTM) Networks Explained Easily 0:28:08
  • 19- How to Implement an RNN-LSTM Network for Music Genre Classification 0:14:29
• Youtube: Advanced Information Retrieval 2021 - TU Wien
  • AIR - 2021 Course Introduction 0:21:39
  • Crash Course IR - Fundamentals 0:46:31
  • Crash Course IR - Evaluation 0:37:15
  • Crash Course IR - Test Collections 0:51:12
  • Word Representation Learning 0:42:02
  • Sequence Modelling with CNNs and RNNs 0:55:04
  • Transformer and BERT Pre-training 0:47:15
  • Introduction to Neural Re-Ranking 0:59:20
  • Transformer Contextualized Re-Ranking 0:49:06
  • Domain Specific Applications 0:38:32
  • Dense Retrieval ❤ Knowledge Distillation 0:59:28
• Youtube: Introduction to Dense Text Representation
  • Introduction to Dense Text Representations - Part 1 0:12:56
  • Introduction to Dense Text Representations - Part 2 0:23:13
  • Introduction to Dense Text Representation - Part 3 0:38:07
  • Training State-of-the-Art Sentence Embedding Models 0:43:43
• Youtube: Fine-tuning a large language model without your own supercomputer
• Youtube: How to build a custom spell checker using python NLP
• Youtube: Transformers 🤗 to Rule Them All? Under the Hood of the AI Recruiter Chatbot 🤖, with Keisuke Inoue
• Youtube: Artificial Intelligence and Natural Language Processing in E-Commerce by Katherine Munro | smec
• Youtube: Abhishek Thakur - Classifying Search Queries Without User Click Data
• Youtube: Chatbots Revisted | by Abhishek Thakur | Kaggle Days Warsaw
• Youtube: Abhishek Thakur - Is That a Duplicate Quora Question?
• Youtube: Design Considerations for building ML-Powered Search Applications - Mark Moyou
• Youtube: Analyze Customer Feedback in Minutes, Not Months
• Youtube: NLP in Feedback Analysis - Yue Ning
• Youtube: Productionizing an unsupervised machine learning model to understand customer feedback
• Youtube: Extracting topics from reviews using NLP - Dr. Tal Perri
• Youtube: Bringing innovation to online retail: automating customer service with NLP
• Youtube: Transform customer service with machine learning (Google Cloud Next '17)
• Youtube: Real life aspects of opinion sentiment analysis within customer reviews - Dr. Jonathan Yaniv
• Youtube: Deep Learning Methods for Emotion Detection from Text - Dr. Liron Allerhand
• Youtube: Learning How to Learn NLP : Developing Introductory Concepts Through Scaffolded Discoveries
• Youtube: What are Transformer Neural Networks?
• Youtube: Applied ML 2020 - 15 - Working with Text Data 1:27:08
• Youtube: Applied ML 2020 - 16 - Topic models for text data 1:18:34
• Youtube: Applied ML 2020 - 17 - Word vectors and document embeddings 1:03:04
• Youtube: A Briefish Introduction to Discourse Representation Theory
• Youtube: HuggingFace Crash Course - Sentiment Analysis, Model Hub, Fine Tuning
• Youtube: Huggingface Course Part 1
• Youtube: Should we care about linguistics?
• Youtube: Transformers From Scratch
  • How-to Use HuggingFace's Datasets - Transformers From Scratch #1 0:14:21
  • Build a Custom Transformer Tokenizer - Transformers From Scratch #2 0:14:17
  • Building MLM Training Input Pipeline - Transformers From Scratch #3 0:23:11
  • Training and Testing an Italian BERT - Transformers From Scratch #4 0:30:38
• In Search of Best Practices for NLP Projects | Ivan Bilan | PyData Pune Meetup | December 2020 0:50:00
• Youtube: Generating and Understanding Natural Language with AI (Aidan Gomez, PhD) 0:52:12
• Youtube: The giant leaps in language technology -- and who's left behind | Kalika Bali
• Youtube: ML for Audio Study Group
  • ML for Audio Study Group - Kick Off

Be familiar with multi-modal machine learning

• CMU: MultiModal Machine Learning Fall 2020
  • Lecture 1.1: Course Introduction
  • Lecture 1.2: Multimodal applications and datasets
  • Lecture 2.1: Basic concepts: neural networks
  • Lecture 2.2: Basic concepts: network optimization
  • Lecture 3.1: Visual unimodal representations
  • Lecture 3.2: Language unimodal representations
  • Lecture 4.1: Multimodal representation learning
  • Lecture 4.2: Coordinated representations
  • Lecture 5.1: Multimodal alignment
  • Lecture 5.2: Alignment and representation
  • Lecture 7.1: Alignment and translation
  • Lecture 7.2: Probabilistic graphical models
  • Lecture 8.1: Discriminative graphical models
  • Lecture 8.2: Deep Generative Models
  • Lecture 9.1: Reinforcement learning
  • Lecture 9.2: Multimodal RL
  • Lecture 10.1: Fusion and co-learning
  • Lecture 10.2: New research directions
• Youtube: W&B Paper Reading Group: MDETR with author Aishwarya Kamath

Be familiar with Recommendation Systems

• Google: Recommendation Systems
• Pluralsight: Understanding Algorithms for Recommendation Systems
• Youtube: Learning to Rank: From Theory to Production - Malvina Josephidou & Diego Ceccarelli, Bloomberg
• Youtube: Learning "Learning to Rank"
• Youtube: Learning to rank search results - Byron Voorbach & Jettro Coenradie [DevCon 2018]

Be able to implement computer vision models

• Article: Common architectures in convolutional neural networks
• Article: Convolutional neural networks
• Article: Densely Connected Convolutional Networks in Tensorflow
• Article: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Article: Multimodal Neurons in Artificial Neural Networks
• Article: Understanding the receptive field of deep convolutional networks
• Article: Deep learning in medical imaging - 3D medical image segmentation with PyTorch
• Article: Intuitive Explanation of Skip Connections in Deep Learning
• Article: Localization and Object Detection with Deep Learning
• Article: Understanding coordinate systems and DICOM for deep learning medical image analysis
• Article: The 9 Deep Learning Papers You Need To Know About (Understanding CNNs Part 3)
• Article: An overview of object detection: one-stage methods
• Article: An overview of semantic image segmentation
• Article: Evaluating image segmentation models
• Article: Semantic Segmentation in the era of Neural Networks
• Article: DenseNet Architecture Explained with PyTorch Implementation from TorchVision
• Article: Group Normalization
• Article: Squeeze and Excitation Networks Explained with PyTorch Implementation
• Article: What is Focal Loss and when should you use it?
• Article: Object Detection for Dummies Part 1: Gradient Vector, HOG, and SS
• Article: Object Detection for Dummies Part 2: CNN, DPM and Overfeat
• Article: Object Detection for Dummies Part 3: R-CNN Family
• Article: A Short Introduction to Generative Adversarial Networks
• Article: Semi-supervised Learning with GANs
• Article: Human Pose Estimation
• Article: How to extract Key-Value pairs from Documents using deep learning
• Article: Building an image search service from scratch
• Article: Breaking Linear Classifiers on ImageNet
• Article: Essential Pil (Pillow) Image Tutorial (for Machine Learning People)
• Article: A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN
• Article: YOLO - You only look once (Single shot detectors)
• Article: NonCompositional
• Article: Part 1: Deep Representations, a way towards neural style transfer
• Article: Looking Inside The Blackbox — How To Trick A Neural Network
• Article: A gentle introduction to OCR
• Article: ECCV 2020: Some Highlights
• AWS: Semantic Segmentation Explained
• Book: Deep Learning for Computer Vision with Python
• Book: Practical Python and OpenCV
• Coursera: Convolutional Neural Networks
• Datacamp: Image Processing in Python
• Google: ML Practicum: Image Classification
• Stanford: CS231N Winter 2016
  • CS231n Winter 2016: Lecture 1: Introduction and Historical Context 1:19:08
  • CS231n Winter 2016: Lecture 2: Data-driven approach, kNN, Linear Classification 1 0:57:28
  • CS231n Winter 2016: Lecture 3: Linear Classification 2, Optimization 1:11:23
  • CS231n Winter 2016: Lecture 4: Backpropagation, Neural Networks 1 1:19:38
  • CS231n Winter 2016: Lecture 5: Neural Networks Part 2 1:18:37
  • CS231n Winter 2016: Lecture 6: Neural Networks Part 3 / Intro to ConvNets 1:09:35
  • CS231n Winter 2016: Lecture 7: Convolutional Neural Networks 1:19:01
  • CS231n Winter 2016: Lecture 8: Localization and Detection 1:04:57
  • CS231n Winter 2016: Lecture 9: Visualization, Deep Dream, Neural Style, Adversarial Examples 1:18:20
  • CS231n Winter 2016: Lecture 10: Recurrent Neural Networks, Image Captioning, LSTM 1:09:54
  • CS231n Winter 2016: Lecture 11: ConvNets in practice 1:15:03
  • CS231n Winter 2016: Lecture 12: Deep Learning libraries 1:21:06
  • CS231n Winter 2016: Lecture 14: Videos and Unsupervised Learning 1:17:36
  • CS231n Winter 2016: Lecture 13: Segmentation, soft attention, spatial transformers 1:10:59
  • CS231n Winter 2016: Lecture 15: Invited Talk by Jeff Dean 1:14:49
• Youtube: Autoencoders - EXPLAINED 0:10:53
• Youtube: Building an Image Captioner with Neural Networks 0:12:54
• Youtube: Convolution Neural Networks - EXPLAINED 0:19:20
• Youtube: Depthwise Separable Convolution - A FASTER CONVOLUTION! 0:12:43
• Youtube: Generative Adversarial Networks - FUTURISTIC & FUN AI ! 0:14:20
• Youtube: How Convolution Works
• Youtube: Mask Region based Convolution Neural Networks - EXPLAINED! 0:09:34
• Youtube: Sound play with Convolution Neural Networks 0:11:57
• Youtube: The Evolution of Convolution Neural Networks 0:24:02
• Youtube: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Paper Explained)
• Youtube: Deep Residual Learning for Image Recognition (Paper Explained)
• Youtube: Evolution of Face Generation | Evolution of GANs 0:12:23
• Youtube: ConvNets Scaled Efficiently 0:13:19
• Youtube: Implementing ResNet from scratch
• Youtube: DETR: End-to-End Object Detection with Transformers (Paper Explained)
• Youtube: Unpaired Image-Image Translation using CycleGANs 0:16:22
• Youtube: Formula Indexing, Search, and Entry in the MathSeer Project 0:52:07
• Youtube: What's new in computer vision | July Queensland AI 1:21:33

Be familiar with graphs and network data

• Datacamp: Network Analysis in Python (Part 1)
• Datacamp: Network Analysis in Python (Part 2)

Be familiar with timeseries and forecasting

• Datacamp: Machine Learning for Finance in Python
• Datacamp: Introduction to Time Series Analysis in Python
• Datacamp: Machine Learning for Time Series Data in Python
• Datacamp: Intro to Portfolio Risk Management in Python
• Datacamp: Financial Forecasting in Python
• Datacamp: Predicting CTR with Machine Learning in Python
• Datacamp: Intro to Financial Concepts using Python
• Datacamp: Fraud Detection in Python
• Datacamp: Forecasting Using ARIMA Models in Python
• Datacamp: Introduction to Portfolio Analysis in Python
• Datacamp: Credit Risk Modeling in Python
• Datacamp: Machine Learning for Marketing in Python
• Udacity: Machine Learning for Trading
• Udacity: Time Series Forecasting
• Youtube: Applied ML 2020 - 21 - Time Series and Forecasting 1:12:36

Be familiar with basics of Reinforcement Learning

• DeepLizard: Reinforcement Learning - Goal Oriented Intelligence
  • Reinforcement Learning Series Intro - Syllabus Overview 0:05:51
  • Markov Decision Processes (MDPs) - Structuring a Reinforcement Learning Problem 0:06:34
  • Expected Return - What Drives a Reinforcement Learning Agent in an MDP 0:06:47
  • Policies and Value Functions - Good Actions for a Reinforcement Learning Agent 0:06:52
  • What do Reinforcement Learning Algorithms Learn - Optimal Policies 0:06:21
  • Q-Learning Explained - A Reinforcement Learning Technique 0:08:37
  • Exploration vs. Exploitation - Learning the Optimal Reinforcement Learning Policy 0:10:06
  • OpenAI Gym and Python for Q-learning - Reinforcement Learning Code Project 0:07:52
  • Train Q-learning Agent with Python - Reinforcement Learning Code Project 0:08:59
  • Watch Q-learning Agent Play Game with Python - Reinforcement Learning Code Project 0:07:22
  • Deep Q-Learning - Combining Neural Networks and Reinforcement Learning 0:10:50
  • Replay Memory Explained - Experience for Deep Q-Network Training 0:06:21
  • Training a Deep Q-Network - Reinforcement Learning 0:09:07
  • Training a Deep Q-Network with Fixed Q-targets - Reinforcement Learning 0:07:35
  • Deep Q-Network Code Project Intro - Reinforcement Learning 0:06:26
  • Build Deep Q-Network - Reinforcement Learning Code Project 0:16:51
  • Deep Q-Network Image Processing and Environment Management - Reinforcement Learning Code Project 0:21:53
  • Deep Q-Network Training Code - Reinforcement Learning Code Project 0:19:46

Be able to perform hyperparameter tuning

• A recipe for training neural networks
• Article: Hyperparameter tuning for machine learning models
• Article: Hacker's Guide to Hyperparameter Tuning
• Article: Environment and Distribution Shift
• Coursera: Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
• Datacamp: Model Validation in Python
• Datacamp: Hyperparameter Tuning in Python
• Google: Testing and Debugging
• Troubleshooting Deep Neural Networks
• Youtube: How do GPUs speed up Neural Network training? 0:08:19
• Youtube: Why use GPU with Neural Networks? 0:09:43
• Youtube: Auto-Tuning Hyperparameters with Optuna and PyTorch

Be familiar with literature on model interpretability

• Article: Model Interpretation Frameworks
• Article: How to leverage Explainable Machine Learning
• Article: TracIn — A Simple Method to Estimate Training Data Influence
• Article: How to Explain the Prediction of a Machine Learning Model?
• NeurIPS 2020: Tutorial on Explaining ML Predictions: State-of-the-art, Challenges, and Opportunities
• Youtube: Jay Alammar - Take A Look Inside Language Models With Ecco
• Youtube: How do we check if a neural network has learned a specific phenomenon?
• Youtube: What is Adversarial Machine Learning and what to do about it? – Adversarial example compilation
• Youtube: SE4AI: Explainability and Interpretability (Part 1) 1:17:45
• Youtube: SE4AI: Explainability and Interpretability (Part 2) 1:21:50

Be able to optimize models for inference

• Article: A Survey of Methods for Model Compression in NLP
• Article: Why you should convert your NLP pipelines to ONNX
• Article: Neural Network Pruning
• Article: FasterAI
• Article: Is the future of Neural Networks Sparse? An Introduction (1/N)
• Article: Sparse Neural Networks (2/N): Understanding GPU Performance.
• Article: Block Sparse Matrices for Smaller and Faster Language Models
• Article: Plunging Into Model Pruning in Deep Learning
• Article: How to accelerate and compress neural networks with quantization
• Article: Scaling up BERT-like model Inference on modern CPU - Part 1

Be able to write unit tests

• Article: Effective testing for machine learning systems
• Article: Unit Testing for Data Scientists
• Article: Testing in Production, the safe way
• Article: How to cheat at unit tests with pytest and Black
• Article: 4 Lesser-Known Yet Awesome Tips for Pytest
• Article: How to Unit Test Deep Learning: Tests in TensorFlow, mocking and test coverage
• Article: Test-Driven Machine Learning Development (Deployment Series: Guide 07)
• Datacamp: Unit Testing for Data Science in Python
• Pluralsight: Test-driven Development: The Big Picture
• Test Driven Development with Python
• Thoughtbot: Fundamentals of TDD
• Udacity: Software Analysis & Testing
• Udacity: Software Testing
• Udacity: Software Debugging
• Youtube: Beyond Accuracy: Behavioral Testing of NLP Models with CheckList | AISC
• Youtube: Lecture 10: ML Testing & Explainability (Full Stack Deep Learning - Spring 2021) 1:41:12
• Youtube: Lab 8: Testing and Continuous Integration (Full Stack Deep Learning - Spring 2021) 0:13:26

Be familiar with ML System Design

• Article: Architecting a Machine Learning Pipeline
• Article: Combining rule engines and machine learning
• Article: Deploying Machine Learning Models: A Checklist
• Article: Getting machine learning to production
• Article: How to build scalable Machine Learning systems — Part 1/2
• Article: How to properly ship and deploy your machine learning model
• Article: How to put machine learning models into production
• Article: Key Concepts for Deploying Machine Learning Models to Mobile
• Article: Machine Learning to Production
• Article: Machine learning is going real-time
• Article: ML Infrastructure Tools for Model Building
• Article: ML Infrastructure Tools for Production (Part 1)
• Article: ML Infrastructure Tools for Production
• Article: How to Deploy a Machine Learning Model
• Article: Building a feature store
• Article: Model artifacts: the war stories
• Article: Machine learning system design
• Article: What is ML model governance?
• Article: Building scalable and efficient ML Pipelines
• Article: What are common dataset challenges at scale?
• Article: How to technically distinguish among data projects?
• Article: Securing ML applications
• Article: Data Pipelines — Agile considerations
• Article: Data Lineage — An Operational perspective
• Article: The Ultimate Guide to Model Retraining
• Book: Machine Learning Systems Design
• Doc: Lecture 3: Data engineering
• Datacamp: Data Engineering for Everyone
• Youtube: Applied ML in Production
  • Objective · Applied ML in Production 0:02:38
  • Solution · Applied ML in Production 0:08:53
  • Evaluation · Applied ML in Production 0:04:02
  • Iteration · Applied ML in Production 0:04:35
  • Annotation · Applied ML in Production 0:14:34
  • Exploratory Data Analysis (EDA) · Applied ML in Production 0:09:02
• Youtube: SE4AI: Software Architecture of AI-Enabled Systems 1:14:24
• Youtube: SE4AI: Invited Talk Molham Aref "Business Systems with Machine Learning" 0:47:53
• Youtube: MLOps #4: Shubhi Jain - Building an ML Platform @SurveyMonkey 0:55:42
• Youtube: MLOps Meetup #6: Mid-Scale Production Feature Engineering with Dr. Venkata Pingali 1:01:35
• Youtube: MLOps meetup #5 High Stakes ML with Flavio CLesio 0:55:27
• Youtube: MLOps meetup #7 Alex Spanos // TrueLayer 's MLOps Pipeline 0:56:17
• Youtube: #11 Machine Learning at scale in Mercado Libre with Carlos de la Torre 0:59:28
• Youtube: MLOps #14: Kubeflow vs MLflow with Byron Allen 0:54:57
• Youtube: MLOps #15 - Scaling Human in the Loop Machine Learning with Robert Munro 0:55:04
• Youtube: MLOps #18 // Nubank - Running a fintech on ML 0:53:19
• Youtube: Feature Stores: An essential part of the ML stack to build great data / Kevin Stumpf - CTO at Tecton 1:05:46
• Youtube: MLOps #31 Path to Production and Monetizing Machine Learning // Vin Vashishta - Data Scientist 0:56:35
• Youtube: MLOps #35: Streaming Machine Learning with Apache Kafka and Tiered Storage // Kai Waehner, Confluent 0:52:50
• Youtube: Luigi in Production // MLOps Coffee Sessions #18 // Luigi Patruno ML in Production 0:47:23
• Youtube: The Current MLOps Landscape // Nathan Benaich & Timothy Chen // MLOps Meetup #43 0:58:31
• Youtube: MLSys Seminars Fall 2020
  • Stanford MLSys Seminar Episode 0: ML + Systems 0:11:49
  • Stanford MLSys Seminar Episode 1: Marco Tulio Ribeiro 1:00:38
  • Stanford MLSys Seminar Episode 2: Matei Zaharia 0:59:44
  • Stanford MLSys Seminar Episode 3: Virginia Smith 1:00:55
  • Stanford MLSys Seminar Episode 4: Alex Ratner 1:13:34
  • Stanford MLSys Seminar Episode 5: Chip Huyen 1:06:44
• Youtube: Xavier Amatriain on Practical Deep Learning Systems (Full Stack Deep Learning - November 2019)
• Article: Decoding Netflix: Metaflow
• Youtube: Avoid cascading failures in a distributed system
• Youtube: How databases scale writes: The power of the log
• Youtube: How to avoid a single point of failure in distributed systems
• Youtube: How to start with distributed systems? Beginner's guide to scaling systems.
• Youtube: What is Distributed Caching? Explained with Redis!
• Youtube: Why do Databases fail? AntiPatterns to avoid!
• Youtube: A friendly introduction to System Design
• Youtube: Designing Instagram: System Design of News Feed
• Youtube: Introduction to NoSQL databases
• Youtube: System Design Basics: Horizontal vs. Vertical Scaling
• Youtube: What is an API and how do you design it?
• Youtube: Service discovery and heartbeats in micro-services
• Youtube: System Design: Tinder as a microservice architecture
• Youtube: What is Load Balancing?
• Youtube: What is a microservice architecture and it's advantages?
• Youtube: What is Consistent Hashing and Where is it used?
• Youtube: What is a Message Queue and Where is it used?
• Youtube: 5 Tips for System Design Interviews
• Youtube: Whatsapp System Design: Chat Messaging Systems for Interviews
• Youtube: Capacity Estimation: How much data does YouTube store daily?
• Youtube: What is Database Sharding?
• Youtube: How Netflix onboards new content: Video Processing at scale
• Youtube: What is the Publisher Subscriber Model?
• Youtube: Distributed Consensus and Data Replication strategies on the server
• Youtube: System design : Design Autocomplete or Typeahead Suggestions for Google search
• Youtube: Relational database index vs. NoSQL index
• Youtube: What's an Event Driven System?
• Youtube: Distributed Consensus and Data Replication strategies on the server
• Youtube: What is an API and how do you design it?
• Youtube: What is Distributed Caching? Explained with Redis!
• Youtube: Service discovery and heartbeats in micro-services
• Youtube: Relational database index vs. NoSQL index
• Youtube: How Netflix onboards new content: Video Processing at scale
• Youtube: How to start with distributed systems? Beginner's guide to scaling systems.
• Youtube: Capacity Estimation: How much data does YouTube store daily?
• Youtube: How databases scale writes: The power of the log
• Youtube: System design : Design Autocomplete or Typeahead Suggestions for Google search
• Youtube: Human-Centric Machine Learning Infrastructure @Netflix

Be able to serve ML models

• Article: The implications of pickling ML models
• Article: Deploy a Keras Deep Learning Project to Production with Flask
• Article: Deploy BERT for Sentiment Analysis as REST API using PyTorch, Transformers by Hugging Face and FastAPI
• Article: Microservice in Python using FastAPI
• Article: Selecting gunicorn worker types for different python web applications.
• Article: Better performance by optimizing Gunicorn config
• Article: Exponential Backoff And Jitter
• Article: How to Serve Models
• Article: MLOps concepts for busy engineers: model serving
• Article: MLOps concepts for busy engineers: model serving
• Article: Understanding TensorFlow Serving
• Article: Serving models using Tensorflow Serving and Docker
• Article: Batch Inference vs Online Inference
• Article: Online batching with Spell serving
• Article: Machine Learning System Design: Real-time processing
• Article: Machine Learning System Design: Models-as-a-service
• Article: What Does it Mean to Deploy a Machine Learning Model? (Deployment Series: Guide 01)
• Article: Software Interfaces for Machine Learning Deployment (Deployment Series: Guide 02)
• Article: Batch Inference for Machine Learning Deployment (Deployment Series: Guide 03)
• Article: The Challenges of Online Inference (Deployment Series: Guide 04)
• Article: Online Inference for ML Deployment (Deployment Series: Guide 05)
• Article: Model Registries for ML Deployment (Deployment Series: Guide 06)
• Video: You trained a machine learning model. Now what?
• Article: How Data Leakage Impacts Machine Learning Models
• Article: 5 Challenges to Running Machine Learning Systems in Production
• Article: Enabling Machine-Learning-as-a-Service Through Privacy Preserving Machine Learning
• Article: Shadow mode deployments
• Cortex Blog
  • Server-side batching: Scaling inference throughput in machine learning
  • How we served 1,000 models on GPUs for $0.47
  • Designing a machine learning platform for both data scientists and engineers
  • How to serve batch predictions with TensorFlow Serving
  • How to deploy Transformer models for language tasks
  • How we scale machine learning model deployment on Kubernetes
  • Why we built a serverless machine learning platform—instead of using AWS Lambda
  • Why we don’t deploy machine learning models with Flask
  • How to deploy machine learning models from a notebook to production
  • A/B testing machine learning models in production
  • How to deploy 1,000 models on one CPU with TensorFlow Serving
  • How to reduce the cost of machine learning inference
  • Improve NLP inference throughput 40x with ONNX and Hugging Face
  • How to deploy PyTorch Lightning models to production
• Django Best Practices
• Udacity: Authentication & Authorization: OAuth
• Udacity: HTTP & Web Servers
• Udacity: Designing RESTful APIs
• Udacity: Client-Server Communication
• Youtube: PyConBY 2020: Sebastian Ramirez - Serve ML models easily with FastAPI
• Youtube: FastAPI from the ground up
• Youtube: Python pydantic Introduction – Give your data classes super powers
• Youtube: PyData Vancouver meetup: cortex.dev : Serving machine learning models in production
• Youtube: Lecture 11A: Deploying ML Models (Full Stack Deep Learning - Spring 2021) 0:53:25
• Youtube: Hands-on serving models using KFserving // Theofilos Papapanagiotou // MLOps Meetup #40 0:57:40
• Youtube: Shawn Scully: Production and Beyond: Deploying and Managing Machine Learning Models

Be able to setup batch inference

• Article: Celery Execution Pools: What is it all about?
• Article: Distill: Why do we need Flask, Celery, and Redis? (with McDonalds in Between)
• Article: Celery: an overview of the architecture and how it works
• Article: Unit Testing Celery Tasks
• Article: Testing Celery Chains
• Article: Task Routing in Celery
• Article: Dynamic Task Routing in Celery
• Article: Dockerize a Celery app with Django and RabbitMQ
• Article: How to call a Celery task from another app
• Article: Distributed Monte Carlo with Celery chords
• Article: An incredibly simple no-frills Celery setup
• Article: 3 Strategies to Customise Celery logging handlers
• Article: Celery task exceptions and automatic retries
• Article: Concurrency and Parallelism
• Article: Celery, docker and the missing startup banner
• Article: Monitoring a Dockerized Celery Cluster with Flower
• Article: Quick Guide: Custom Celery Task Logger
• Article: Celery on Docker: From the Ground up
• Article: Auto-reload Celery on code changes

Be able to build interactive UI for models

• Article: Build and Deploy a Dashboard with Streamlit
• Article: New layout options for Streamlit

Be able to use Docker for containerization

• Article: How To Pass Environment Info During Docker Builds
• Article: Pass Docker Environment Variables During The Image Build
• Article: Setting Default Docker Environment Variables During Image Build
• Article: Docker Explained Visually, For Non-Technical Folks
• Article: Tensorflow in Docker
• Article: Enough Docker to be Dangerous
• Article: How Docker Can Help You Become A More Effective Data Scientist
• Article: Deploying conda environments in (Docker) containers - how to do it right
• Article: Configuring Gunicorn for Docker
• Article: How to scale services using Docker Compose
• Article: A Beginner-Friendly Introduction to Containers, VMs and Docker
• Article: Smaller Docker images with Conda
• Pluralsight: Docker and Containers: The Big Picture
• Article: Docker for Machine Learning – Part I
• Article: Docker for Machine Learning – Part II
• Article: Docker for Machine Learning – Part III
• Article: Using Docker to Generate Machine Learning Predictions in Real Time
• Article: Connection refused? Docker networking and how it impacts your image
• Article: Faster or slower: the basics of Docker build caching
• Article: Where’s your code? Debugging ImportError and ModuleNotFoundErrors in your Docker image
• Article: A tableau of crimes and misfortunes: the ever-useful docker history
• Article: Broken by default: why you should avoid most Dockerfile examples
• Article: A review of the official Dockerfile best practices: good, bad, and insecure
• Article: The best Docker base image for your Python application (February 2021)
• Article: A deep dive into the official Docker image for Python
• Article: Using Alpine can make Python Docker builds 50× slower
• Article: Building on solid ground: ensuring reproducible Docker builds for Python
• Article: Installing system packages in Docker with minimal bloat
• Article: Less capabilities, more security: minimizing privilege escalation in Docker
• Article: Avoiding insecure images from Docker build caching
• Article: Build secrets in Docker and Compose, the secure way
• Article: Security scanners for Python and Docker: from code to dependencies
• Article: The high cost of slow Docker builds
• Article: Faster Docker builds with pipenv, poetry, or pip-tools
• Article: Elegantly activating a virtualenv in a Dockerfile
• Article: Poetry vs. Docker caching: Fight!
• Article: Speed up pip downloads in Docker with BuildKit’s new caching
• Article: Multi-stage builds #1: Smaller images for compiled code
• Article: Multi-stage builds #2: Python specifics—virtualenv, –user, and other methods
• Article: Multi-stage builds #3: Why your build is surprisingly slow, and how to speed it up
• Article: Configuring Gunicorn for Docker
• Article: Activating a Conda environment in your Dockerfile
• Article: Shrink your Conda Docker images with conda-pack
• Article: What’s running in production? Making your Docker images identifiable
• Article: Your Docker build needs a smoke test
• Article: Docker BuildKit: faster builds, new features, and now it’s stable
• Article: Docker vs. Singularity for data processing: UIDs and filesystem access
• Article: Where’s that log file? Debugging failed Docker builds
• Article: An Introduction to Kubernetes for Data Scientists
• Article: How to Use Kubernetes Pods for Machine Learning
• Article: Kubernetes Jobs for Machine Learning
• Article: Kubernetes CronJobs for Machine Learning
• Article: Kubernetes Deployments for Machine Learning
• Article: Kubernetes Services for Machine Learning
• “Let’s use Kubernetes!” Now you have 8 problems
• Article: Kubernetes for Python Developers: Part 1
• Doc: Environment variables in Compose
• Pluralsight: Docker and Kubernetes: The Big Picture
• Udacity: Scalable Microservices with Kubernetes
• Youtube: Docker
• Youtube: Why Your Web Server Should Log to Stdout (Especially with Docker)

Be able to use Cloud

• Article: A deep dive into AWS spot instance interruptions
• Article: Getting started with large-scale ETL jobs using Dask and AWS EMR
• Datacamp: Cloud Computing for Everyone
• Pluralsight: AWS Developer: The Big Picture
• Pluralsight: AWS Networking Deep Dive: Virtual Private Cloud (VPC)
• Pluralsight: AWS VPC Operations
• Pluralsight: Building Applications Using Elastic Beanstalk
• Udemy: AWS Concepts
• Udemy: AWS Certified Developer - Associate 2018
• Whitepaper: Architecting for the Cloud AWS Best Practices
• Whitepaper: AWS Well-Architected Framework
• Whitepaper: AWS Security Best Practices
• Whitepaper: Blue/Green Deployments on AWS
• Whitepaper: Microservices on AWS
• Whitepaper: Optimizing Enterprise Economics with Serverless Architectures
• Whitepaper: Practicing Continuous Integration and Continuous Delivery on AWS
• Whitepaper: Running Containerized Microservices on AWS

Be familiar with serverless architecture

• Udemy: Serverless Concepts
• Whitepaper: Serverless Architectures with AWS Lambda
• Youtube: Deploying a machine learning model to the cloud using AWS Lambda

Be able to monitor ML models

• Article: Production Machine Learning Monitoring: Outliers, Drift, Explainers & Statistical Performance
• Article: How to Monitor Models
• Article: The Playbook to Monitor Your Model’s Performance in Production
• Article: Monitoring your Machine Learning Model
• Article: Preventing model drift with continuous monitoring and deployment using Github Actions and Algorithmia Insights
• Article: Continuous monitoring for data projects
• Article: Lessons Learned from 15 Years of Monitoring Machine Learning in Production
• Article: Why is it Important to Monitor Machine Learning Models?
• Article: Using Statistical Distances for Machine Learning Observability
• Article: The Model’s Shipped; What Could Possibly go Wrong?
• Article: Quality assurance in data science
• Youtube: Instrumentation, Observability & Monitoring of Machine Learning Models
• Article: Incident Management in Machine Learning Systems
• Article: ML Infrastructure Tools — ML Observability
• Youtube: MLOps #24 Monitoring the ML stack // Lina Weichbrodt 0:55:32
• Youtube: Josh Wills: Visibility and Monitoring for Machine Learning Models
• Youtube: Lecture 11B: Monitoring ML Models (Full Stack Deep Learning - Spring 2021) 0:36:55
• Youtube: OpML '20 - How ML Breaks: A Decade of Outages for One Large ML Pipeline
• Youtube: MLOps #28 ML Observability // Aparna Dhinakaran - Chief Product Officer at Arize AI 0:55:04
• Youtube: MLOps #29 Continuous Evaluation & Model Experimentation // Danny Ma - Founder of Sydney Data Science 1:00:46
• Youtube: SE4AI: Quality Assessment in Production 1:18:45
• Youtube: SE4AI: Infrastructure Quality, Deployment and Operations 1:04:54

Be able to perform load testing

• Youtube: Loading Testing with Python

Be able to perform A/B testing

• Article: Multi-Armed Bandit (MAB) – A/B Testing Sans Regret
• Article: When to Run Bandit Tests Instead of A/B/n Tests
• Article: A/B Testing Machine Learning Models (Deployment Series: Guide 08)
• Datacamp: Customer Analytics & A/B Testing in Python
• Udacity: A/B Testing
• Udacity: A/B Testing for Business Analysts
• Youtube: Hypothesis testing with Applications in Data Science 0:10:33

Be proficient in Python

• Article: No Really, Python's Pathlib is Great
• Article: When to switch to Python 3.9
• Article: A deep dive on Python type hints
• Article: I wish I knew these things when I learned Python
• Article: Python Concurrency: The Tricky Bits
• Article: The Complete Python Development Guide
• Article: Speeding Up Python with Concurrency, Parallelism, and asyncio
• Article: Speed Up Your Python Program With Concurrency
• Article: A Python prompt into a running process: debugging with Manhole
• Regex For Noobs (like me!) - An Illustrated Guide
• Book: A Byte of Python
• Book: Learn Python The Hard way
• Book: Python 201
• Book: The Python 3 Standard Library By Example
• Book: Writing Idiomatic Python 3
• Calmcode: ray
• Codecademy: Learn Python
• Cognitiveclass.ai: Python for Data Science
• Datacamp: Python for R Users
• Datacamp: Python for Spreadsheet Users
• Datacamp: Importing Data in Python (Part 1)
• Datacamp: Intermediate Python for Data Science
• Datacamp: Python Data Science Toolbox (Part 1)
• Datacamp: Python Data Science Toolbox (Part 2)
• Datacamp: Intro to Python for Finance
• Datacamp: Writing Efficient Python Code
• Datacamp: Writing Functions in Python
• Datacamp: Working with Dates and Times in Python
• edX: Introduction to Python for Data Science
• edX: Programming with Python for Data Science
• Google's Python Class
• Treehouse: Python Basics
• TheNewBoston: Python Programming Tutorials
• Youtube: Python 3 Programming Tutorial - Regular Expressions / Regex with re
• Youtube: Python Tutorial: re Module - How to Write and Match Regular Expressions (Regex)
• Youtube: Python Concurrency and Multithreading
• Youtube: Aaron Richter- Parallel Processing in Python| PyData Global 2020
• Youtube: The Clean Architecture in Python

Have a general understanding of other parts of the stack

• Book: Refactoring UI
• Codecademy: Learn HTML
• Codecademy: Learn SASS
• Codecademy: Make a website
• Codecademy: Learn ReactJS: Part I
• Codecademy: Learn ReactJS: Part II
• Codecademy: Learn JavaScript
• Codecademy: Jquery Track
• Codecademy: Learn Ruby
• Code School: Fundamentals of Design
• Code School: Blasting Off with Bootstrap
• (ES6) - Beau teaches JavaScript
• Pluralsight: UX Fundamentals
• Pluralsight: HTML, CSS, and JavaScript: The Big Picture
• Pluralsight: CSS Positioning
• Pluralsight: Introduction to CSS
• Pluralsight: CSS: Specificity, the Box Model, and Best Practices
• Pluralsight: CSS: Using Flexbox for Layout
• Pluralsight: Using The Chrome Developer Tools
• Thoughtbot: Design for Developers
• Treehouse: HTML
• Treehouse: Javascript Booleans
• Udacity: ES6 - JavaScript Improved
• Udacity: Intro to Javascript
• Udacity: Object Oriented JS 1
• Udacity: Object Oriented JS 2
• Udemy: Understanding Typescript

Be familiar with fundamental Computer Science concepts

• Article: Asymptotic Analysis Explained with Pokémon: A Deep Dive into Complexity Analysis
• Book: Grokking Algorithms
• Codecademy: Big O
• Crashcourse: Computer Science
• Khan Academy: Data Structures
• Udacity: Intro to Algorithms
• Udacity: Intro to Computer Science
• Udacity: Intro to Theoretical Computer Science
• Udacity: Programming Languages
• Udacity: Networking for Web Developers

Be able to apply proper software engineering process

• Pluralsight: Security Awareness: Basic Concepts and Terminology
• Pluralsight: Secure Software Development
• Pluralsight: Clean Architecture: Patterns, Practices, and Principles
• Thoughtbot: Software Development Process
• Thoughtbot: Refactoring
• Udacity: Design of Computer Programs
• Udacity: Product Design
• Udacity: Rapid Prototyping
• Udacity: Software Development Process

Be able to efficiently use a text editor

• Article: Work remotely with PyCharm, TensorFlow and SSH
• Article: Python remote debugging with PyCharm, CUDA, and Conda
• Article: How To Use Visual Studio Code for Remote Development via the Remote-SSH Plugin
• Article: Docker as Remote Interpreter for PyCharm Professional
• Youtube: Getting Started with Python in Visual Studio Code
• Youtube: VSCode Keyboard Shortcuts For Productivity
• Youtube: Getting Started with Jupyter Notebooks in VS Code
• Youtube: Notebooks in VS Code Are Getting Revamped!
• Youtube: Getting Started with PyTorch in VS Code
• Youtube: What every GitHub user should know about VS Code - GitHub Satellite 2020
• VS Code and GitHub
• Visual Studio Code Crash Course

Be able to communicate and collaborate well

• Google: Technical Writing
• Book: Emotional Intelligence
• Book: How to Win Friends & Influence People
• Book: Influence: The Psychology of Persuasion
• Book: Leaders Eat Last: Why Some Teams Pull Together and Others Don't
• Book: Multipliers: How the Best Leaders Make Everyone Smarter
• Book: Soft Skills: The software developer's life manual
• Book: The New One Minute Manager
• Calmcode: Remote Work
• Youtube: Building a psychologically safe workplace | Amy Edmondson | TEDxHGSE
• Youtube: A short introduction to LaTeX and Overleaf

Be familiar with the hiring pipeline

• Article: What You Need to Know Before Considering a PhD
• Article: Advice to aspiring data scientists: start a blog
• Article: Systems Design Interview Guide
• Article: A Guide to Cold Emailing
• Article: Uber Data Science Interview
• Article: Google Data Science Interview
• Article: Facebook Data Science Interview
• Article: Acing the Data Science Interview — Part 1
• Article: Acing the Data Science Interview — Part 2
• Article: Amazon Data Science Interview
• Article: Microsoft Data Science Interview
• Article: Microsoft Data Science Interview
• Article: Apple AI Interview Questions — Acing the AI Interview
• Article: Salesforce Data Science Interview— Acing the AI Interview
• Article: LinkedIn Data Science Interview
• Article: Netflix Data Science Interview
• Article: Walmart Data Science Interview
• Article: Twitter Data Science Interview
• Article: Ebay Data Science Interview
• Article: Zillow Data Science Interview
• Article: Intel Data Science Interview
• Article: Adobe Data Science Interview
• Article: Tesla Data Science Interview
• Article: IBM Data Science Interview
• Article: Top Data Science Interview Questions & Answers
• Article: Top Data Science Interview Questions & Answers — Part 2
• Article: Top Data Science Interview Questions & Answers — Part 3
• Article: Data Science Interview Questions and Solutions — Linear and Logistic regression
• Article: Capital One Data Science Interview
• Article: Paypal Data Science Interview
• Article: Airbnb Data Science Interview
• Article: Spotify Data Science Interview Questions
• Article: Yelp Data Science Interview
• Article: Twitch Data Science Interview
• Article: Oracle Data Science Interview
• Article: Citrix Data Science Interview
• Article: Quora Data Science Interview
• Article: Splunk Data Science Interview
• Article: JP Morgan Data Science Interview
• Article: Stripe Data Science Interview Questions
• Article: Box Data Science Interview
• Article: Instacart Data Science Interview Questions
• Article: Square Data Science Interview
• Article: AmEx Data Science Interview
• Article: Citibank Data Science Interview
• Article: Sprint Data Science Interview
• Article: Dropbox Data Science Interview
• Article: Booking.com Data Science Interview
• Article: Lyft Data Science Interview
• Article: Expedia Data Science Interview
• Article: Shopify Data Science Interview Questions
• Article: Goldman Sachs Data Science Interviews
• Article: Workday Data Science Interviews
• Article: Acing Data Science Interviews
• Article: Analysis of Data Science Interview Questions
• Article: Visa Data Science Interviews
• Article: Data Science Quiz— Part 1
• Book: Machine Learning Interviews
• Datacamp: Preparing for Statistics Interview Questions in Python
• Datacamp: Practicing Machine Learning Interview Questions in Python
• Datacamp: Kaggle Competition
• Udacity: Optimize your GitHub
• Udacity: Strengthen Your LinkedIn Network & Brand
• Udacity: Data Science Interview Prep
• Udacity: Full-Stack Interview Prep
• Udacity: Refresh Your Resume
• Udacity: Craft Your Cover Letter
• Udacity: Technical Interview
• Youtube: Panel Discussion: Do I need a PhD to work in ML? (Full Stack Deep Learning - Spring 2021)
• Youtube: The Importance of Writing in a Tech Career - Eugene Yan
• Youtube: How to prepare for Machine Learning interviews- Part 1 | Applied AI Course
• Youtube: How to prepare for Machine Learning interviews- Part 2 | Applied AI Course
• Youtube: Guest Lecture - Chip Huyen - Machine Learning Interviews - Full Stack Deep Learning
• Youtube: Tutorial: Technical Blogging for Python Programmers

Broaden Perspective

• Book: Atomic Habits
• Book: Deep Work
• Book: Outliers: The Story of Success
• Book: Platform: The Art and Science of Personal Branding
• Book: Rich Dad Poor Dad
• Book: The Power of Broke
• Book: The 10X Rule
• Book: The Millionaire Fastlane
• Book: The Subtle Art of Not Giving a F**k
• Calmcode: Pomodoro
• Youtube: Why specializing early doesn't always mean career success | David Epstein
• Youtube: Chamath Palihapitiya, Founder and CEO Social Capital, on Money as an Instrument of Change
• Youtube: How to Build a Personal Monopoly with Jack Butcher
• Youtube: How to Use Twitter
• Youtube: A. Jesse Jiryu Davis - Write an Excellent Programming Blog - PyCon 2016
• Youtube: The Great ML Stagnation (Mark Saroufim and Dr. Mathew Salvaris)
• Youtube: What Machine Learning Can Teach Us About Life: 7 Lessons - Talk Python Live Stream
• Youtube: Ross Tuck - Things I Believe Now That I'm Old at Laracon EU 2014
• Youtube: "How to teach programming (and other things)?" by Felienne Hermans 0:52:08
• Youtube: The secrets of learning a new language | Lýdia Machová