Deep Learning and the Game of Go

Appendix B. The backpropagation algorithm

Chapter 5 introduced sequential neural networks and feed-forward networks in particular. We briefly talked about the backpropagation algorithm, which is used to train neural networks. This appendix explains in a bit more detail how to arrive at the gradients and parameter updates that we simply stated and used in chapter 5.

We’ll first derive the backpropagation algorithm for feed-forward neural networks and then discuss how to extend the algorithm to more-general sequential and nonsequential networks. Before going deeper into the math, let’s define our setup and introduce notation that will help along the way.

A bit of notation

In this section, you’ll work with a feed-forward neural network with ...