midpoint (Neural Network Toolbox)

Midpoint weight initialization function

W = midpoint(S,PR)

midpoint is a weight initialization function that sets weight (row) vectors to the center of the input ranges.

midpoint(S,PR) takes two arguments,

S - Number of rows (neurons).

PR - R x 2 matrix of input value ranges = [Pmin Pmax].

and returns an S x R matrix with rows set to (Pmin+Pmax)'/2.

Examples

Here initial weight values are calculated for a 5 neuron layer with input elements ranging over [0 1] and [-2 2].

W = midpoint(5,[0 1; -2 2])

You can create a standard network that uses midpoint to initialize weights by calling newc.

To prepare the weights and the bias of layer i of a custom network to initialize with midpoint:

1.: Set net.initFcn to 'initlay'. (net.initParam will automatically become initlay's default parameters.)

3.: Set each net.inputWeights{i,j}.initFcn to 'midpoint'. Set each net.layerWeights{i,j}.initFcn to 'midpoint';

To initialize the network call init.