ML learning resources: list of resources I personally use to learn Machine Learning

A personal note. This is a living document - list of resources I use to learn Machine Learning, in no particular order. I, most of the time, read the books first to give me enough foothold, before strengthen my comprehension with videos and courses. It’s not always that way, though. In some other occasions, where I feel the subject is dry and not really fun to learn, I tend to go straight to the implementations (usually by watching online courses), before working backward from there to learn the fundamentals (usually by reading books).

Books:

• ✓ Designing Machine Learning System
• ~ Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd Edition
• ~ Feature Engineering for Machine Learning
• ~ Mathematics for Machine Learning
• Machine Learning Design Patterns
• AI and Machine Learning for Coders
• Reliable Machine Learning
• Practical Machine Learning for Computer Vision
• Neural Networks and Deep Learning

Online courses:

• ✓ ZTM AI, Machine Learning, and Data Science
• ~ ZTM PyTorch for Deep Learning Bootcamp

Videos:

• ✓ Stanford CS229 - Andrew Ng
• Stanford CS231N - Deep Learning for Computer Vision
• Stanford CS224N - NLP with Deep Learning
• Intro to RL - Google Deepmind
• Practical Deep Learning for Coders, Lecture Notes
• Mathematics for Machine Learning Specialization
• Andrej Karpathy
• ∞ 3Blue1Brown
  • The essence of calculus
  • The essence of linear algebra
• ∞ StatQuest
  • StatQuest - Video Index

Conferences & journals - recent AI developments and trends:

• NeurIPS, ICML, ICLR, AAAI, IJCAI
• Distill

Meta-learning (learning how to learn):

• Advices on PhD study, Andrew Ng - tldr; read a lot of papers, then replicate them.

Etc:

• ML Glossary
• ML Roadmap
• The incredible Pytorch

---

Legend:

• ✓ = Done!
• ~ = In progress. Getting there…
• ✗ = Not started yet
• ∞ = References only