Hacker News Reader

I agree. A solid understanding of why it works is still a requirement if you want to do something productive with neural networks.

But as someone who has been taking video courses and seen youtube videos, somehow this was the final step I needed to get started on my idea. It was easy to follow along, the code was nice and clean (most importantly without convoluted variable naming), and the immediately-interactive code made it quick to test a few things, rather than having to fork a project, NPM install a thousand dependencies and then actually do some coding.

It would be great to add some context to the demo.

Where does one go to learn the math behind it?

That depends if you know calculus, preferably multivariable.

Here is a simple start! https://www.youtube.com/watch?v=N4gDikiec8E

Module one of Andre Karpathy's course is the most intuitive explanation I've seen. Working through backprop equations was a major hassle until I read those notes.

http://cs231n.github.io/