Neural Network Toolbox

trains

Sequential order incremental training w/learning functions

Syntax

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

info = trains(code)

Description

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

trains trains a network with weight and bias learning rules with sequential updates. The sequence of inputs is presented to the network with updates occurring after each time step.

This incremental training algorithm is commonly used for adaptive applications.

trains 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 after training the network with its weight and bias learning functions returns:

• net - Updated network.

  TR - Training record.

  • TR.time steps - Number of time steps.

    TR.perf - performance for each time step.

  Ac - Collective layer outputs.

  El - Layer errors.

Training occurs according to trains's training parameter shown here with its default value:

• net.trainParam.passes 1 Number of times to present sequence

Dimensions for these variables are:

• Pd - No x NixTS 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 an 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)

trains(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 trains for adapting by calling newp or newlin.

To prepare a custom network to adapt with trains:

1. Set net.adaptFcn to 'trains'.

   • (This will set net.adaptParam to trains'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 allow the network to adapt:

1. Set weight and bias learning parameters to desired values.
2. Call adapt.

See newp and newlin for adaption examples.

Algorithm

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

See Also

newp, newlin, train, trainb, trainc, trainr

trainrp

trainscg