How the backpropagation algorithm works

This chapter is the most theoretical of the six chapters in Neural Networks and Deep Learning. It derives the equations for gradient descent and provides strong mathematical intuitions for why they actually make sense. (These types of intuitions were why we decided to read Neural Networks and Deep Learning as a group.) Finally, the chapter contains some code for implementing gradient descent in the neural network we coded from scratch in the first chapter.

Error! Looks like your browser can't display PDFs. Try using an updated version of Chrome or Firefox.