trainb

(To be removed) Batch training with weight and bias learning rules

trainb 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 = 'trainb'
[net,tr] = train(net,...)


Description

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

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

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

trainb trains a network with weight and bias learning rules with batch updates. The weights and biases are updated at the end of an entire pass through the input data.

Training occurs according to trainb’s training parameters, shown here with their default values:

net.trainParam.epochs	1000	Maximum number of epochs to train
net.trainParam.goal	0	Performance goal
net.trainParam.max_fail	6	Maximum validation failures
net.trainParam.min_grad	1e-6	Minimum performance gradient
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

You can create a standard network that uses trainb by calling linearlayer.

To prepare a custom network to be trained with trainb,

1. Set net.trainFcn to 'trainb'. This sets net.trainParam to trainb’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 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

Each weight and bias is updated according to its learning function after each epoch (one pass through the entire set of input vectors).

Training stops when any of these conditions is met:

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

• Performance is minimized to the goal.

• The maximum amount of time is exceeded.

• Validation performance (validation error) has increased more than max_fail times since the last time it decreased (when using validation).

Version History

Introduced before R2006a

R2026a: trainb will be removed

trainb 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.