Backpropagation Algorithm

Backpropagation Algorithm


Backpropagation, at its core, simply consists of repeatedly applying the chain rule through all of the possible paths in our network. It is a dynamic programming algorithm where we reuse intermediate results to calculate the gradient.
The core of backpropagation is taking all error derivatives from a layer to compute error derivatives of the layer that comes before it

Resources:
http://briandolhansky.com/blog/2013/9/27/artificial-neural-networks-backpropagation-part-4
https://www.youtube.com/watch?v=59Hbtz7XgjM
http://cs231n.github.io/optimization-2/

Comments