AI/ML
Notes are brief qualitative descriptions to help with course selection.
YouTube Courses
- Stanford CS229 by Andrew Ng
- Classical Machine Learning. A good point to start with
- Neural Networks: Zero to Hero - Andrej Karpathy
- More focused towards DL and Transformers, might not be for absolute beginners
Other video courses platforms
- Machine Learning with Scikit-learn, PyTorch & Hugging Face | Coursera
- A classic material for learning machine learning. Complete and polished.
- Practical Deep Learning for Coders - Practical Deep Learning
- Has more of a modern feel and leans more towards DL. Not a classical ML course
- Deep Learning by Andrew Ng
- A very popular course on Deep Learning and is recommended by many people. A very good course if your main goal is Neural Networks
- Machine Learning by freeCodeCamp
Text Based Courses
- microsoft/ML-For-Beginners: 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
- Still updated and maintained till this date (date of writing this wiki). Personal Bias. Text based guides are much better than video courses
- Machine Learning | Google for Developers
- Seems very practical. Good for a crash course.
- Can be used as reference or for quick overview of topics like regression, classification etc.
- Home - Made With ML by Anyscale
- Non-traditional
- Good while making a proper ML project
Books for ML
- Mathematics for Machine Learning | Companion webpage to the book “Mathematics for Machine Learning”. Copyright 2020 by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong. Published by Cambridge University Press.
- Is like Handbook of CP.
- good for going through quickly. While building intuition leveraging different resources
- Understanding Deep Learning
- DL resource
Misc
- Hugging Face - Learn
- They have very specific courses. Not complete course. But very high quality imo.
- Deep Learning Online Courses | NVIDIA