HackerBackpropagation calculus | Deep Learning Chapter 4
3Blue1BrownYouTube ↗
Further reading 1
Caption notes
Trace one weight through a weighted input, an activation and the cost. Multiplying the local sensitivities gives a derivative; repeating that calculation toward earlier layers propagates it backward.
Creator’s caption track ↗Original passages · 2
This right here is the chain rule, where multiplying together these three ratios gives us the sensitivity of c to small changes in WL.Also, and this is where the idea of propagating backwards comes in, you can see how sensitive this cost function is to the activation of the previous layer.