NewMultiLayerNet returns an underlying Network conceptuallyorganised into layers Layers variable = slice of integers representing node count at each layer.

NewNetwork creates a new Network containing size neurons, with a certain number dedicated to input, and a pre-defined neural function applied to the rest.

LinearFunction doesn't modify the value.

SigmoidForward function does S(t) = \frac{1}{1 + e^{-t}}.

Rectified Linear function https://www.wikiwand.com/en/Rectifier_(neural_networks).

MultiLayerNet creates a new Network which is conceptually organised into layers, zero or more of which are hidden.

Network represents the most general neural network possible Weights are stored in a dense matrix, each can have its own NeuralFunction.

First function is always the forward activation function Second function is always the backward activation function.

LayerFuncs are vectorised layer value transformation functions (e.g.