Neural Network Toolbox™

Symmetric random weight/bias initialization function

Syntax

• W = rands(S,PR)
  M = rands(S,R)
  v = rands(S);
  

Description

rands is a weight/bias initialization function.

rands(S,PR) takes

S	Number of neurons
PR	R x 2 matrix of R input ranges

and returns an S-by-R weight matrix of random values between -1 and 1.

rands(S,R) returns an S-by-R matrix of random values. rands(S) returns an S-by-1 vector of random values.

Examples

Here three sets of random values are generated with rands.

• rands(4,[0 1; -2 2])
  rands(4)
  rands(2,3)
  

Network Use

To prepare the weights and the bias of layer i of a custom network to be initialized with rands,

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

To initialize the network, call init.

See Also

randnr, randnc, initwb, initlay, init

Provide feedback about this page

randnr

randtop

© 1984-2008- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS