Batch training with weight and bias learning rules
net.trainFcn = 'trainb'
[net,tr] = train(net,...)
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 ( |
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 |
You can create a standard network that uses trainb by calling
linearlayer.
To prepare a custom network to be trained with trainb,
Set net.trainFcn to 'trainb'.
This sets net.trainParam to trainb’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.
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 has increased more than max_fail times since
the last time it decreased (when using validation).