initnw (Neural Network Toolbox)

Nguyen-Widrow layer initialization function

net = initnw(net,i)

initnw is a layer initialization function which initializes a layer's weights and biases according to the Nguyen-Widrow initialization algorithm. This algorithm chooses values in order to distribute the active region of each neuron in the layer evenly across the layer's input space.

initnw(net,i) takes two arguments,

net - Neural network.

i - Index of a layer.

and returns the network with layer i's weights and biases updated.

Network Use

You can create a standard network that uses initnw by calling newff or newcf.

To prepare a custom network to be initialized with initnw:

1.: Set net.initFcn to 'initlay'. (This will set net.initParam to the empty matrix [ ] since initlay has no initialization parameters.)

2.: Set net.layers{i}.initFcn to 'initnw'.

To initialize the network call init. See newff and newcf for training examples.

Algorithm

The Nguyen-Widrow method generates initial weight and bias values for a layer, so that the active regions of the layer's neurons will be distributed roughly evenly over the input space.

Advantages over purely random weights and biases are:

1.: Few neurons are wasted (since all the neurons are in the input space).

2.: Training works faster (since each area of the input space has neurons). The Nguyen-Widrow method can only be applied to layers...

with a bias,
with weights whose "weightFcn" is dotprod,
with "netInputFcn" set to netsum.

If these conditions are not met then initnw uses rands to initialize the layer's weights and biases.