ML Checklist

Posted on Edited on In Views:

Resources for essential topics of Machine Learning and Deep learning, including Natural language processing (NLP), Computer Vision (CV), Reinforcement Learning (RL), Self-Supervised Learning (SSL), etc.

Some Great Youtubers

  • Andrej Karpathy
  • Yannic Kilcher
  • Edan Meyer
  • StatQuest with Josh Starmer
  • Mu Li

Resources

  • A curated list of AI resources
  • The Practical Guides for Large Language Models
  • Large Language Model Course
  • Online textbook: Deep Dive DL
  • Deep Learning Book

Yes you should understand backprop

https://colab.research.google.com/drive/1WV2oi2fh9XXyldh02wupFQX0wh5ZC-z-?usp=sharing

Bessel's Correction

https://docs.python.org/3/library/copy.html

Must learn

  • Neural Networks: Zero to Hero
  • Stanford 231n: Convolutional Neural Networks
    • Youtube video
    • Notes (very useful!)
  • Cousera: Deep Learning Specialization
  • Stanford 224n: NLP
  • C230, Deep Learning 2018, by Andrew Ng
  • Practical Deep Learning (Transformer and Difussion Model)
  • NLP Course | For You
  • Stanford CS25: Transformers United V3
    • Youtube videos
  • Stanford XCS224U: Natural Language Understanding
    • Youtube videos
  • Stanford CS234: Reinforcement Learning
  • Deep Reinforcement Learning, UC Berkeley, CS285
  • UvA Deep Learning Tutorials
    • Tutorial6 is about Transformer.
  • Transformers from Scratch

General

  • Standord CS330, Deep Multi-Task and Meta Learning

    • --> Videos

  • Convex Optimization I, Stanford, EE364A

  • Advanced Probability, CMU, 36-752

  • Stochastic Calculus and Stochastic Control, Princeton, ACM 217

  • Theoretical Foundations of Reinforcement Learning, University of Alberta, CMPUT 605

  • Efficient AI

  • Stanford CS 224R: Deep Reinforcement Learning

  • Stanford CS238 Decision Making under Uncertainty

  • CS221: Artificial Intelligence: Principles and Techniques

  • CS 224W: Machine Learning with Graphs

  • CS 246W: Mining Massive Datasets

  • CS237b: Algebraic Error Correcting Codes

Math

NLP

  • LSTM

Probabilistic Graphical Models

  • Stanford CS228
  • Youtube: CMU 10-708
  • CMU 10-708 Notes

RL

Others

https://web.stanford.edu/class/cs250/

https://pwn.college/

CPU-free Computing: A Vision with a Blueprint

CV

UVA CG

RL

https://spinningup.openai.com/en/latest/user/introduction.html

Statistics

https://openintro-ims2.netlify.app/07-model-slr

https://statproofbook.github.io/I/ToC

https://www.cs.cmu.edu/~aarti/Class/10704_Fall16/

Classical papers