Best self-study materials for Machine Learning/Deep Learning/Natural Language Processing - Free online data science study resources
25 Mar 2020 | Data Science Machine Learning Deep LearningData science study resources
Updated March 20, 2021
As the field matures, there is an abundance of resources to study data science nowadays. At the same time, it is getting more difficult to search and locate high-quality study material with an increasing level of information overload. Therefore, I started gathering and organizing study resources for contemporary data science. Here, I present study materials that I highly recommend. Most materials are either (1) ones that I have personally studied and reviewed or (2) ones repeated recommended by my colleagues and friends. Hence, this is not a comprehensive set of resources for studying data science for anyone, but rather a curated set of materials from my (biased) point of view. Also, I will update and refresh the resources from time to time, so stay tuned!
How to use resources in this page
Though this is a personally curated list of resources, it is A LOT. I do not expect anyone, including me, to be familiar with all materials and topics that are covered in this list. However, what I recommend is try out as many as relevant materials that you can before you embark your journey to a specific field of data science. I do not want to specifically regard one material better than another since it is a matter of taste. In the reinforcement learning terminology, you will need to explore a bit before you find a satisficing material for your studying. And this list will help you exploring while saving your most valuable resource, time. Come back to this list whenever you need to search for a new material that can guide your journey.
Machine learning / Data mining
Books
- Pattern Recognition and Machine Learning by Chris Bishop
- Data Mining: Concepts and Techniques by Jiawei Han
- Machine Learning by Tom Mitchell
Course materials/Lectures
- CS229: Machine Learning (Stanford University, Dr. Andrew Ng)
- Data Mining: Principles and Algorithms (UIUC, Dr. Jiawei Han)
- MIS464: Data Analytics (University of Arizona, Dr. Hsinchun Chen)
- Introduction to Machine Learning for Coders (fast.ai, Jeremy Howard)
Deep learning
Books
- Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
- Deep Learning with Python by François Chollet
- Neural Networks and Deep Learning by Michael Nielsen
Course materials/Lectures
- DS-GA 1008 Deep Learning (NYU, Dr. Yann LeCun & Alfredo Canziani)
- CS W182/282A Designing, Visualizing and Understanding Deep Neural Networks (UC Berkeley, Dr. Sergey Levine)
- CS230 Deep Learning (Stanford, Dr. Andrew Ng)
- Deep Learning (Coursera, Dr. Andrew Ng)
- CS231n: Convolutional Neural Networks for Visual Recognition (Stanford University, Dr. Fei-Fei Li)
- Practical Deep Learning for Coders (fast.ai, Jeremy Howard)
- DeepLearningZeroToAll (HKUST, Dr. Sung Kim)
Natural language processing
Books
- Speech and Language Processing by Dan Jufrasky and James Martin
Course materials/Lectures
- CS224n: Natural Language Processing with Deep Learning (Stanford University, Dr. Chris Manning)
- CS224U: Natural Language Understanding (Stanford University, Dr. Bill MacCartney)
- A Code-First Introduction to Natural Language Processing (fast.ai, Jeremy Howard)
Network analysis
Books
- Network Science by Albert-László Barabási
- Networks, Crowds, and Markets: Reasoning About a Highly Connected World by David Easley and Jon Kleinberg
Course materials/Lectures
- CS224W: Machine Learning with Graphs (Stanford University, Dr. Jure Leskovec)
Reinforcement learning
Books
- Reinforcement Learning: An Introduction by Richard Sutton & Andrew Barto
Course materials/Lectures
- Reinforcement learning (UCL, Dr. David Silver)
- CS234: Reinforcement Learning (Stanford University, Dr. Emma Brunskill)
- CS285: Deep Reinforcement Learning (UC Berkeley, Dr. Sergey Levine)
Linear algebra/Statistics
Course materials/Lectures
- CS109: Probability for Computer Scientists (Stanford, Dr. David Varodayan)
- Statistics 110: Probability (Harvard, Dr. Joe Blitzstein)
- Computational Linear Algebra for Coders (fast.ai)
- Statistics for Applications (MIT, Dr. Phillipe Rigollet)
- Introduction to Probability and Statistics (MIT)