The Matrix Calculus You Need For Deep Learning

parrt.cs.usfca.edu

This paper is an attempt to explain all the matrix calculus you need in order to understand the training of deep neural networks. We assume no math knowledge beyond what you learned in calculus 1, and provide links to help you refresh the necessary math where needed.

Didn't take linear algebra (or forgotten most of what you learned)? No problem, the authors have written this just for you. You'll feel much more confident deploying deep learning models when you can follow the math all the way down.

Read more...
Linkedin

Want to receive more content like this in your inbox?