Hidden Layers

Go to [[Week 2 - Introduction]] or back to the [[Main AI Page]] Part of the page on [[Deep Learning]]

Hidden layers are layers of neurons between the input and output layers that allow the neural network to identify features in the input.

But ...

If a network includes too many neurons in a hidden layer, it can overfit and simply memorize the input patterns, which limits the network’s ability to generalize. Too few neurons in the hidden layer can result in the network being unable to represent the input-space features and also limit the networks’ ability to generalize. In general, the smaller the network (fewer neurons and weights), the better the network.