setwb

(To be removed) Set all network weight and bias values with single vector

setwb 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

net = setwb(net,wb)


Description

This function sets a network’s weight and biases to a vector of values.

net = setwb(net,wb) takes the following inputs:

net	Neural network
wb	Vector of weight and bias values

Examples

Set Network's Weights and Biases

This example shows how to set and view a network’s weight and bias values.

Create and configure a network.

[x,t] = simplefit_dataset;
net = feedforwardnet(3);
net = configure(net,x,t);
view(net)

This network has three weights and three biases in the first layer, and three weights and one bias in the second layer. So, the total number of weight and bias values in the network is 10. Set the weights and biases to random values.

net = setwb(net,rand(10,1));

View the weight and bias values

net.IW{1,1}
net.b{1}

ans =

    0.1576
    0.9706
    0.9572


ans =

    0.5469
    0.9575
    0.9649

Version History

Introduced in R2010b

R2026a: setwb will be removed

setwb will be removed in a future release.

To learn more about initializing and customizing neural network learnable parameters, see these examples and topics:

• Compare Layer Weight Initializers

• Specify Custom Weight Initialization Function

• Neural Network Weight Tying

• Initialize Learnable Parameters for Model Function

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.