Resources

There is a vibrant community of machine learning developers and open-source packages for scientific research. Many of the links below have provided inspiration or borrowed content for this module.

(Image by John Kitchen)

General Python

• Python for Physicists

• Python for Chemists

• Phind AI helper

Tools and Benchmarks

• Classical ML: scikit-learn; scikit-opt

• Deep Learning: pytorch; tensorflow; jax; keras

• Materials benchmarks: Matbench; Matbench-Discovery; JARVIS-Leaderboard

• Materials focused tools: matminer; automatminer; elementembeddings; matgl; dscribe

• Molecular focused tools: deepchem; stk; chemiscope

• Model tracking: mlflow; wandb

• Other lists: Awesome Materials Informatics; Awesome Self Driving Labs; Awesome Generative AI; Atomistic ML

Books

• Applications of Artificial Intelligence in Chemistry

• Bayesian Computation

• Data Analysis: A Bayesian Tutorial

• Deep Learning for Molecules and Materials

• Dive into Deep Learning

• Geometric Deep Learning

• Interpretable Machine Learning

• Machine Learning in Materials Science

• Reinforcement Learning and Optimal Control

• Understanding Deep Learning

Papers

• Best Practices in Machine Learning for Chemistry

• Machine Learning for Molecular and Materials Science

• Machine Learning for Materials Scientists: An Introductory Guide toward Best Practices

Videos

• Materials Cloud (Webinars)

• Materials Project (Webinars)

• Materials Informatics (Taylor Sparks)

• Neural networks (3Blue1Brown)

• Python for Science (John Kitchin)

• Statquest with Josh Starmer

Other Courses

• Automated Experiments

• AI For Everyone

• Data Driven Chemistry

• Deep Neural Networks

• Gentle Introduction to Graph Neural Networks

• Homemade Machine Learning

• Introduction to Machine Learning in Chemistry

• Materials Informatics

• Mathematics for Machine Learning Specialisation

• Mathematics in Materials

• Machine Learning for Everyone

• Machine Learning for Materials

• Machine Learning Refined

• Materials Informatics

• Microsoft ML for Beginners

• ML for Chemistry

• ML in Materials

• ML Training Resources

• Numerics of ML

• Practical Deep Learning

• Stanford ML Cheat Sheets