Random order incremental training with learning functions
net.trainFcn = 'trainr'
[net,tr] = train(net,...)
trainr is not called directly. Instead it is called by train for networks whose net.trainFcn property is set to 'trainr', thus:
net.trainFcn = 'trainr' sets the network trainFcn property.
[net,tr] = train(net,...) trains the network with 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.
Training occurs according to trainr training parameters, shown here with their default values:
Maximum number of epochs to train
|net.trainParam.max_fail||6||Maximum validation failures|
Epochs between displays (NaN for no displays)
Generate command-line output
Show training GUI
Maximum time to train in seconds
You can create a standard network that uses trainr by calling competlayer or selforgmap. To prepare a custom network to be trained with trainr,
To train the network,
See help competlayer and help selforgmap for training examples.
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.
Performance is minimized to the goal.
The maximum amount of time is exceeded.