Linear Algebra for Deep Learning: Matrix Algebra

Linear Algebra for Deep Learning: Matrix Algebra(quantstart.com)

131 points by shogunmike 8 years ago | 8 comments

This is a nice intro to linear algebra but doesn't really get into how it's related to deep learning. A good read is Vector, Matrix, and Tensor Derivatives[0], which goes into the linear algebra needed in multi-layer neural networks, specifically during the backpropogation phase.

[0] http://cs231n.stanford.edu/vecDerivs.pdf

shogunmike 8 years ago | |

You're correct - it doesn't get into the deep learning aspect yet.

This article is in fact the second part of a larger planned series. The idea is to present more depth than a "quick refresher" that seems to be common to a lot of blog posts, but far less material than would be found in a 10-week (or single semester) undergraduate course.

Thanks for the Stanford link. I'll check it out.

adamkochanowicz 8 years ago |

Awesome! I have some Khan Academy courses queued up to learn linear algebra, but this is more targeted and useful.

nerdponx 8 years ago | |

The best intro to linear algebra, bar none, is the MIT OpenCourseware Intro to Linear Algebra, recordings of a course taught in 2005 by Prof. Gilbert Strang: https://ocw.mit.edu/courses/mathematics/18-06-linear-algebra...

shogunmike 8 years ago | | |

Indeed - I recommended Strang's book in this article and the previous one.

paulgb 8 years ago | |

I'd highly recommend this set of videos: https://youtu.be/kjBOesZCoqc

brudgers 8 years ago | | |

Also Gilbert Strang's lectures: https://www.youtube.com/watch?v=ZK3O402wf1c&list=PL49CF3715C...