I believe in a bottom-up learning strategy, in which we have strong foundations before diving deep into the Top (Research). However, while in the research, it is also helpful to refresh the foundations for better performance. Thus, the Foundations of any field play a crucial role in deciding the height of our research in that field.

Below is the collection of Machine Learning Basics, Maths, and Programming resources for building solid foundations in Machine Learning. I have divided Foundation learning into two phases: one “Preliminary Learning (PL)” should be completed before going into research, while the other “Continuous Learning Stage (CLS) “ can be done parallel to research (you change according to your wish if required)

1. Preliminary Learning (PL)
2. Continuous Learning Stage (CLS)

Machine Learning Basics

• CS156 ML (Caltech, Prof. Yasir)
• CS229 ML (Stanford, Spring’22)
• CS231n CNN for CV (Stanford, notes)

ML course at IITH

AI5000 (FOML/PRML) - Resources

Maths

Probability and Statistics

• ProbabilityCourse website
• [CLS] Stats 110: Probability (Harvard)
• [CLS] Brilliant (Proba and Stats section)
• CS772A Probabilistic Machine Learning (IIT K)
• [CLS] CS 228 Probabilistic Graphical Models (Stanford, notes)
• Mathematics for ML (Proba & Stats Chapter)

Linear Algebra

• 18.065 (MIT, Prof. Gilbert)
• [CLS] 18.06SC, (MIT, Prof. Gilbert)
• Mathematics for ML (Linear Algebra Section)
• [CLS] Brilliant (Linear Algebra section)
• Essence of Linear Algebra (3Blue1Brown)

Optimisation

• [CLS] NPTEL Real Analysis (IIT B
• ELL 780 (course notes, IITD)
• [CLS] Brilliant (Optimisation section)
• Essence of calculus (3Blue1Brown)

Programming

• DS Handbook (available in android as well)
• DSA GFG Videos
• [CLS] Algorithms (Abdul Barri videos)
• [CLS] Brilliant (CS section)