The Essential NLP, AI, and ML Classics Shared by Thom Wolf: A Self-Learner's Guide

Thom Wolf, a co-founder of Hugging Face, started his career in Physics rather than Computer Science. In 2015, Thom was attracted by the new ML/AI revolution as many of the methods were just re-branded statistical physics approaches. He started his online education and shared the list of resources he used.

Reading list

1. The "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Provides a great overview of current deep learning techniques.

2. "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig. Covers all pre-neural-network tools and methods.

3. "Machine Learning: A Probabilistic Perspective" by Kevin P. Murphy. Covers probabilistic approach and Bayesian tools.

4. "Information Theory, Inference, and Learning Algorithms" by David MacKay. Provides a great explanation of probabilities and information theory.

5. "The Book of Why: The New Science of Cause and Effect" by Pearl, Judea. A good introduction to Causality.

6. "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto.

Natural Language Processing: three great resources

1. Kyunghyun Cho's lecture notes on "Natural Language Processing with Representation Learning".

2. Yoav Goldberg's book on "Neural Network Methods in Natural Language Processing" and its older free version.

3. Jacob Eisenstein's textbook on "Natural Language Processing."

Online courses

• Computational Probability and Inference (6.008.1x) from edX

• Probabilistic Graphical Models Specialization from Coursera

Also, check our article about Hugging Face 👇🏼

Every day our post helpful lists and bite-sized explanations on our Twitter. Please join us there: