trainwb1 (Neural Network Toolbox)

Neural Network Toolbox

Search Help Desk

trainwb1

See Also

By-weight-and-bias network training function

Syntax

[net,tr] = trainwb1(net,Pd,Tl,Ai,Q,TS,VV)

info = trainwb1(code)

Description

trainwb1 is a network training function which updates each weight and bias according to its learning function. At each epoch trainwb1 randomly chooses just one input vector (or sequence) to present to the network.

trainwb1(net,Pd,Tl,Ai,Q,TS,VV) takes these inputs,

net - Neural network.

Pd - Delayed input vectors.

Tl - Layer target vectors.

Ai - Initial input delay conditions.

Q - Batch size.

TS - Time steps.

VV - Either empty matrix [] or structure of validation vectors.

and returns,

net - Trained network.

TR - Training record of various values over each epoch:

TR.epoch - Epoch number.

TR.perf - Training performance.

TR.index - Index of presented input vector (or sequence).

Training occurs according to the trainwb1's training parameters shown here with their default values:

net.trainParam.epochs 100 Maximum number of epochs to train

net.trainParam.show 25 Epochs between showing progress

net.trainParam.time inf Maximum time to train in seconds

Dimensions for these variables are:

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

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

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

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

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

trainwb1 does not implement validation or test vectors, so arguments VV and TV are ignored.

trainwb1(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 trainwb1 with newc or newsom.

To prepare a custom network to be trained with trainwb1:

1.: Set net.trainFcn to 'trainwb1'. (This will set net.trainParam to trainwb1'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 train the network:

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

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

3.: Call train.

See newc and newsom for training examples.

Algorithm

For each epoch a vector (or sequence) is chosen randomly and presented to the network and then the weight and bias values are updated accordingly.

Training stops when any of these conditions are met:

1.: The maximum number of epochs (repetitions) is reached.

2.: The maximum amount of time has been exceeded.