zarak / ml-roadmap

Collection of resources for self-studying mathematics and machine learning.

ml-roadmap

A collection of resources for self-studying machine learning, with a focus on mathematics. An attempt is made to select canonical math textbooks, but they are primarily selected on the basis of the availability of corresponding video lectures. This list is not meant to be comprehensive, but rather focused and tailored to my own goals.

Mathematics

Topic	Lecture Videos	Textbook
Multivariable Calculus and Linear Algebra	Math 23a (no longer public)	Vector Calculus, Linear Algebra, and Differential Forms: A Unified Approach by Hubbard and Hubbard
Real Analysis	Real Analysis: Lectures by Professor Francis Su Principles of Mathematical Analysis: Winston Ou	Principles of Mathematical Analysis by Walter Rudin
Algebra	Math 122	Algebra by Michael Artin
Topology	Topology by Bruno Zimmerman	Topology by James Munkres
Algebraic Topology	Algebraic Topology - Pierre Albin Algebraic Topology - N J Wildberger	Algebraic Topology by Allen Hatcher
Category Theory	Category Theory Foundations - Steve Awodey	Category Theory by Steve Awodey

Machine Learning MOOCs

Title	University	Programming Language
Deep Learning Specialization	Stanford	Python
Statistical Learning	Stanford	R
Learning from Data	Caltech	Any
Neural Networks for Machine Learning	University of Toronto	Any
Machine Learning	Columbia	Python, MATLAB
Probabilistic Graphical Models	Stanford	MATLAB/Octave
Machine Learning with Python	MIT	Python
Machine Learning for Healthcare	MIT	Python

Computer Science MOOCs

1. Software Construction in Java, MIT
2. Advanced Software Construction in Java, MIT
3. Algorithms I and Algorithms II, Princeton University
4. Algorithms Specialization, Stanford University

Other Relevant MOOCs

1. Convex Optimization, Stanford University
2. Automata Theory, Stanford University
3. Introduction to Probability - The Science of Uncertainty, MIT
4. Advanced Linear Models for Data Science 1: Least Squares and Advanced Linear Models for Data Science 2: Statistical Linear Models, Johns Hopkins University

Challenges

1. Kaggle
2. DrivenData

Miscellaneous

1. SciPy 2016: Scientific Computing with Python Conference
2. JMLR
3. Deep Learning papers
4. Practical Deep Learning for Coders, Part 1
5. 6.S094: Deep Learning for Self-Driving Cars
6. CS224d: Deep Learning for Natural Language Processing
7. CS231n: Convolutional Neural Networks for Visual Recognition
8. CS 294: Deep Reinforcement Learning, Spring 2017
9. Bayesian Data Analysis Course