All Projects → unnati-xyz → Intro To Deep Learning For Nlp

unnati-xyz / Intro To Deep Learning For Nlp

The repository contains code walkthroughs which introduces Deep Learning in the field of Natural Language Processing.

Projects that are alternatives of or similar to Intro To Deep Learning For Nlp

Cenpy
Explore and download data from Census APIs
Stars: ✭ 104 (-0.95%)
Mutual labels:  jupyter-notebook
Faceaging By Cyclegan
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Ml4music Workshop
Machine Learning for Music and Sound Synthesis workshop
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Content Aws Mls C01
AWS Certified Machine Learning - Specialty (MLS-C01)
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Spring2019 tutorials
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Kaggle Ds Bowl 2018 Baseline
Full train/inference/submission pipeline adapted to the competition from https://github.com/matterport/Mask_RCNN
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Team Learning
主要展示Datawhale的组队学习计划。
Stars: ✭ 1,397 (+1230.48%)
Mutual labels:  jupyter-notebook
Anomaly Detection
Anomaly detection algorithm implementation in Python
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Openplan
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Deepai
Detection of Accounting Anomalies using Deep Autoencoder Neural Networks - A lab we prepared for NVIDIA's GPU Technology Conference 2018 that will walk you through the detection of accounting anomalies using deep autoencoder neural networks. The majority of the lab content is based on Jupyter Notebook, Python and PyTorch.
Stars: ✭ 104 (-0.95%)
Mutual labels:  jupyter-notebook
D2l Torch
《动手学深度学习》 PyTorch 版本
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Unet Segmentation In Keras Tensorflow
UNet is a fully convolutional network(FCN) that does image segmentation. Its goal is to predict each pixel's class. It is built upon the FCN and modified in a way that it yields better segmentation in medical imaging.
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Simple adversarial examples
Repo of simple adversarial examples on vanilla neural networks trained on MNIST
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Bert Loves Chemistry
bert-loves-chemistry: a repository of HuggingFace models applied on chemical SMILES data for drug design, chemical modelling, etc.
Stars: ✭ 103 (-1.9%)
Mutual labels:  jupyter-notebook
How To Generate Art Demo
This is the code for "How to Generate Art - Intro to Deep Learning #8' by Siraj Raval on YouTube
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Tensorflow2.0 Examples
🙄 Difficult algorithm, Simple code.
Stars: ✭ 1,397 (+1230.48%)
Mutual labels:  jupyter-notebook
Face Classification
Face model to classify gender and race. Trained on LFWA+ Dataset.
Stars: ✭ 104 (-0.95%)
Mutual labels:  jupyter-notebook
Cgoes
Research by Carlos Góes
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook
Pixel2style2pixel
Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation"
Stars: ✭ 1,395 (+1228.57%)
Mutual labels:  jupyter-notebook
Tf objectdetection api
Tutorial on how to create your own object detection dataset and train using TensorFlow's API
Stars: ✭ 105 (+0%)
Mutual labels:  jupyter-notebook

##Introduction to Deep Learning and NLP

Requirements to run the notebooks

  • Anaconda for python 2
  • Keras

Link to the slides

Topics:

  1. What is deep learning?
  2. Motivation: Some use cases where it has produced state-of-art results
  3. Basic building blocks of Neural networks (Neuron, activation function, back propagation algorithm, gradient descent algorithm)
  4. Supervised learning (multi-layer perceptron, recurrent neural network) - notebook
  5. Introduction to word2vec - notebook
  6. Introduction to Recurrent Neural Networks
  7. Text classification using RNN - notebook
  8. Impact of GPUs (Some practical thoughts on hardware and software)
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].