adaptwb (Neural Network Toolbox)

Neural Network Toolbox

Search Help Desk

adaptwb

See Also

By-weight-and-bias network adaption function

Syntax

[net,Ac,El] = adaptwb(net,Pd,Tl,Ai,Q,TS)

info = adaptwb(code)

Description

adaptwb is a network function which updates each weight and bias according to its learning function.

adaptwb takes these inputs,

net - Neural network.

Pd - Delayed inputs.

Tl - Layer targets.

Ai - Initial input conditions.

Q - Batch size.

TS - Time steps.

After training the network with its weight and bias the learning functions returns,

net - Updated network.

Ac - Collective layer outputs.

El - Layer errors.

Adaption occurs according to the adaptwb's training parameter, shown here with its default value:

net.adaptparam.passes 1 Number of passes through sequence

Dimensions for these variables are:

Pd - No x Ni x TS cell array, each element P{i,j,ts} is a Zij x Q matrix.

Tl - Nl x TS cell array, each element P{i,ts} is a Vi x Q matrix or [].

Ai - Nl x LD cell array, each element Ai{i,k} is an Si x Q matrix.

Ac - Nl x (LD+TS) cell array, each element Ac{i,k} is an Si x Q matrix.

El - Nl x TS cell array, each element El{i,k} is an Si x Q matrix or [].

where

Ni = net.numInputs

Nl = net.numLayers

LD = net.numLayerDelays

Ri = net.inputs{i}.size

Si = net.layers{i}.size

Vi = net.targets{i}.size

Zij = Ri * length(net.inputWeights{i,j}.delays)

adaptwb(code) returns useful information for each code string:

'pnames' - Names of training parameters.

'pdefaults' - Default training parameters.

Network Use

You can create a standard network that uses adaptwb by calling newp or newlin.

To prepare a custom network to adapt with adaptwb:

1.: Set net.adaptfcn to 'adaptwb'. (This will set net.adaptparam to adaptwb's default parameters.)

2.: Set each net.inputweights{i,j}.learnfcn to a learning function. Set each net.layerweights{i,j}.learnfcn to a learning function. Set each net.biases{i}.learnfcn to a learning function. (Weight and bias learning parameters will automatically be set to default values for the given learning function.)

To allow the network to adapt:

1.: Set net.adaptparam properties to desired values.

2.: Set weight and bias learning parameters to desired values.

3.: Call adapt.

See newp and newlin for adaption examples.

Algorithm

Each weight and bias is updated according to its learning function after each step in the input sequence.