Some useful resources I found while learning about machine learning.

Andrew Ng’s machine learning classes are a great place to start. For a less mathematical introduction, his Coursera class is also good. The Youtube series is from 2008, but the fundamentals haven’t changed. Finish the course before moving on to deep learning.

[Stanford CS229 lecture series] [Lecture notes]

## Linear Algebra

A proper geometric introduction to linear algebra

[Essence of linear algebra video series]

## SVMs

Geometric intuition of SVMs (max margin separating hyperplanes)

Rigorous mathematical derivation

[Stanford CS 229 lecture series]

Understanding kernels

[Intuitive explanation of how the kernel trick works]

[Wikipedia article on Hilbert Space]

[Wikipedia article on Similarity Measure]

[Quora post on choosing a kernel for text classification]

## Softmax Regression

Intro to softmax:

[CS 231n lecture video] [CS 231n notes]

[Deep learning tutorial on softmax] [Softmax gradient derivation]

## Neural Networks

Intro to neural networks:

Understanding how to optimize gradient descent

[Yann LeCun’s paper *Efficient Backprop*]