deeplearning.ai step-by-step guide
This project provides a step-by-step guide for you easy to follow the Coursera Deep Learning Specialization course. Learning notes and python code will be included in this repo as well as other helpful references. For more details about the series courses:
- deeplearning.ai: Announcing new Deep Learning courses on Coursera
- Coursera - Deep Learning Specialization
- 网易微专业 - 深度学习工程师
Table of Contents
Prerequisite
Some basic machine learning background is good for understanding the materials. Since this is a deep learning course, machine learning knowlodge will not be covered much. For you who do not have any machine learning background, I think Andrew Ng's Machine Learning course is a great starting point. Hope you can find some helpful learning notes here: Coursera机器学习笔记(〇)-目录
Programming Environment
Python is used for this course. Coursera provides a cloud jupyter notebook environment called coursera hub, you can finish your programming assignments directly on the coursera website. The following package/framework should be installed if you would like to run code on your own environment:
Anaconda is a good choice for settling your own environment.
Usage
All the materials of each course including notes/code can be found in the corresponding subfolder. Please note that the code is not solutions to the assignment but you can get hints from it.
Getting Started
Course1: Neural Networks and Deep Learning
- Week 1: Introduction to deep learning
- Week 2: Neural Networks Basics
- Week 3: Shallow neural networks
- Week 4: Deep Neural Networks
Course2: Improving Deep Neural Networks
- Wee1: Practical aspects of Deep Learning
- Wee2: Optimization algorithms
- Wee3: Hyperparameter tuning, Batch Normalization and Programming Frameworks
Course3: Structuring Machine Learning Projects
Course4: Convolutional Neural Networks
N/A
Course5: Sequence Models
N/A
