Neural Network Toolbox

trainc

Cyclical order incremental training with learning functions

Syntax

[net,TR,Ac,El] = trainc(net,Pd,Tl,Ai,Q,TS,VV,TV)

info = trainc(code)

Description

trainc is not called directly. Instead it is called by train for networks whose net.trainFcn property is set to 'trainc'.

trainc trains a network with weight and bias learning rules with incremental updates after each presentation of an input. Inputs are presented in cyclic order.

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

• net -- Neural network

  Pd -- Delayed inputs

  Tl -- Layer targets

  Ai -- Initial input conditions

  Q -- Batch size

  TS -- Time steps

  VV -- Ignored

  TV -- Ignored

and returns,

• net -- Trained network

  TR -- Training record of various values over each epoch:

  • TR.epoch -- Epoch number

    TR.perf -- Training performance

  Ac -- Collective layer outputs

  El -- Layer errors

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

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

  net.trainParam.goal 0 Performance goal

  net.trainParam.show 25 Epochs between displays (NaN for no                                  displays)

  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 Pd{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 or []

            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)

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

trainc(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 trainc by calling newp.

To prepare a custom network to be trained with trainc

1. Set net.trainFcn to 'trainc'.

• (This will set net.trainParam to trainc default parameters.)

2. Set each net.inputWeights{i,j}.learnFcn to a learning function.
3. Set each net.layerWeights{i,j}.learnFcn to a learning function.
4. 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 newp for training examples.

Algorithm

For each epoch, each vector (or sequence) is presented in order to the network with the weight and bias values updated accordingly after each individual presentation.

Training stops when any of these conditions are met:

• The maximum number of epochs (repetitions) is reached.
• Performance has been minimized to the goal.
• The maximum amount of time has been exceeded.

See Also

newp, newlin, train

trainbr

traincgb

© 1994-2005 The MathWorks, Inc.