January 2019
Intermediate to advanced
390 pages
9h 16m
English
Let's first gain a little understanding of the technique behind the backpropagation algorithm. If you remember from the previous section, the loss function at the output neuron is as follows:

You can see that it's unchanged, and so the weight connecting hidden neuron k to the output neuron j would be given as follows:

Applying the chain rule of differentiation, this reduces to the following:

In the preceding equation, ...
Read now
Unlock full access