Neural Network Toolbox

trainr

Random order incremental training with learning functions.

Syntax

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

info = trainr(code)

Description

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

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

trainr(net,Pd,Tl,Ai,Q,TS,VV) 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 trainr'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)

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

trainr(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 trainr by calling newc or newsom.

To prepare a custom network to be trained with trainr

1. Set net.trainFcn to 'trainr'.

• (This will set net.trainParam to trainr's 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 newc and newsom for training examples.

Algorithm

For each epoch, all training vectors (or sequences) are each presented once in a different random order with the network and 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

trainoss

trainrp

© 1994-2005 The MathWorks, Inc.