We implemented two types of Perceptron to define the ones that handle external input and the ones internally connected to one another. That's why the basic Perceptron class derives from the latter one. The FeedForward function handles the inputs and irrigates them along the network. Finally, the function for back propagation is the one responsible for adjusting the weights. This weight adjustment is the emulation of learning.
How it works...
Get Unity 2018 Artificial Intelligence Cookbook - Second Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
