trainru

(To be removed) Unsupervised random order weight/bias training

trainru will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

net.trainFcn = 'trainru'
[net,tr] = train(net,...)


Description

trainru is not called directly. Instead it is called by train for networks whose net.trainFcn property is set to 'trainru', thus:

net.trainFcn = 'trainru' sets the network trainFcn property.

[net,tr] = train(net,...) trains the network with trainru.

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

Training occurs according to trainru training parameters, shown here with their default values:

net.trainParam.epochs	1000	Maximum number of epochs to train
net.trainParam.show	25	Epochs between displays (NaN for no displays)
net.trainParam.showCommandLine	false	Generate command-line output
net.trainParam.showWindow	true	Show training GUI
net.trainParam.time	Inf	Maximum time to train in seconds

Network Use

To prepare a custom network to be trained with trainru,

1. Set net.trainFcn to 'trainru'. This sets net.trainParam to trainru’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 are automatically 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.

Algorithms

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 is met:

• The maximum number of epochs (repetitions) is reached.

• The maximum amount of time is exceeded.

Version History

Introduced in R2010b

R2026a: trainru will be removed

trainru will be removed in a future release.

To learn more about customizing training algorithms, see these examples and topics:

• Custom Training Loops

• Define Custom Learning Rate Schedule

• Train Network Using Custom Training Loop

• Compare Custom Solvers Using Custom Training Loop

• Speed Up Deep Neural Network Training

• Accelerate Custom Training Loop Functions

• Evaluate Deep Learning Experiments by Using Metric Functions

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.