Helpful Resources

Video resources:

• John Kitchin’s youtube channel

  • Very relevant, starts at the basics and works up. Accompanying PDF textbooks available too!

  • The notes for 06-623 are also very helpful. https://kitchingroup.cheme.cmu.edu/f19-06623/

  • Prof. Kitchin also self-publishes guides to many of these topics. Ask Prof. Ulissi for a discount code if you want to buy something!

Relevant courses (including videos/slides/etc):

• Collated list of relevant courses by topic area: https://github.com/dair-ai/ML-YouTube-Courses

• Stanford CS229 Lectures by Andrew Ng

  • More details than needed for this course, but great if you’re interested in the underlying methods

  • Andrew Ng is extremely well known for his work in AI/ML

• NYU Deep Learning in Pytorch

  • General overview of deep learning models with pytorch examples

• Berkeley Data 8

  • More statistics focused, but excellent examples and good background on the stats

  • Textbook: Berkeley Data 8 Textbook (Inferential Thinking)

• CMU 10-601

  • Slides, lectures, etc all available

  • Lecture recordings available for CMU students through panopto

Online textbooks:

• Python Numerical Methods

• deep learning for molecules & materials

  • Great overview of how to apply deep learning models to materials (graph networks, force fields, etc)

• Python Data Science Handbook

• The Scikit-Learn MOOC

Tutorials for common ML software packages we’ll use:

• pytorch tutorial

• scikit-learn

  • User guide and examples are both excellent!