Backpropagation calculus, Deep learning, chapter 4

Brought to you by you: This one is a bit more symbol heavy, and that s actually the point. The goal here is to represent in somewhat more formal terms the intuition for how backpropagation works in part 3 of the series, hopefully providing some connection between that video and other texts, code that you come across later. For more on backpropagation: Music by Vincent Rubinetti: Video timeline 0:00 Introduction 0:38 The Chain Rule in networks 3:56 Computing relevant derivatives 4:45 What do the derivatives mean 5:39 Sensitivity to weights, biases 6:42 Layers with additional neurons 9:13 Recap 3blue1brown is a channel about animating math, in all senses of the word animate. And you know the drill with You