Unsupervised random order weight/bias training
net.trainFcn = 'trainru'
[net,tr] = train(net,...)
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 |
| Maximum number of epochs to train |
net.trainParam.show |
| Epochs between displays ( |
net.trainParam.showCommandLine |
| Generate command-line output |
net.trainParam.showWindow |
| Show training GUI |
net.trainParam.time |
| Maximum time to train in seconds |
To prepare a custom network to be trained with trainru,
Set net.trainFcn to 'trainru'.
This sets net.trainParam to trainru’s default
parameters.
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,
Set net.trainParam properties to desired
values.
Set weight and bias learning parameters to desired values.
Call train.
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.