midpoint :: Functions (Neural Network Toolbox™)

midpoint

Purpose

Midpoint weight initialization function

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 Q matrix of input value ranges = [Pmin Pmax]

`S`	Number of rows (neurons)
`PR`	`R` x `Q` matrix of input value ranges = `[Pmin Pmax]`

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

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

Set net.initFcn to 'initlay'. (net.initParam automatically becomes initlay's default parameters.)
Set net.layers{i}.initFcn to 'initwb'.
Set each net.inputWeights{i,j}.initFcn to 'midpoint'. Set each net.layerWeights{i,j}.initFcn to 'midpoint'.

To initialize the network, call init.