randsmall

(To be removed) Small random weight/bias initialization function

randsmall will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

W = randsmall(S,PR)
M = rands(S,R)
v = rands(S)

Description

randsmall is a weight/bias initialization function.

W = randsmall(S,PR) takes

S

Number of neurons

PR

R-by-2 matrix of R input ranges

and returns an S-by-R weight matrix of small random values between –0.1 and 0.1.

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

Examples

Here three sets of random values are generated with rands.

randsmall(4,[0 1; -2 2])
randsmall(4)
randsmall(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 'randsmall'.

  4. Set each net.layerWeights{i,j}.initFcn to 'randsmall'.

  5. Set each net.biases{i}.initFcn to 'randsmall'.

To initialize the network, call init.

Version History

Introduced in R2010b

collapse all

See Also

| (Statistics and Machine Learning Toolbox) | (Statistics and Machine Learning Toolbox) | | |

Topics