Uses of Class
deepnetts.net.train.BackpropagationTrainer

Packages that use BackpropagationTrainer

Package	Description
deepnetts.net.train	Training algorithms and related utilities.

Uses of BackpropagationTrainer in deepnetts.net.train

Methods in deepnetts.net.train that return BackpropagationTrainer

Modifier and Type	Method	Description
BackpropagationTrainer	TrainingEvent.getSource()	Gets the source of the event.
BackpropagationTrainer	BackpropagationTrainer.setBatchMode(boolean batchMode)	Sets flag whether to use batch mode during the training.
BackpropagationTrainer	BackpropagationTrainer.setBatchSize(int batchSize)	Batch size is number of training examples after which network's weights are adjusted.
BackpropagationTrainer	BackpropagationTrainer.setCheckpointEpochs(int checkpointEpochs)	On how many epochs the snapshots of the trained network should be created.
BackpropagationTrainer	BackpropagationTrainer.setDropout(float dropout)	Dropout is a technique to prevent overfitting, which skips adjusting weights for some neurons with given probability.
BackpropagationTrainer	BackpropagationTrainer.setEarlyStopping(boolean earlyStopping)	Early stopping stops training if it starts converging slow, and prevents overfitting.
BackpropagationTrainer	BackpropagationTrainer.setEarlyStoppingMinLossChange(float earlyStoppingMinLossChange)	Early stopping stops training if the error/loss start converging to slow.
BackpropagationTrainer	BackpropagationTrainer.setEarlyStoppingPatience(int earlyStoppingPatience)	How many epochs to wait to see if the loss is lowering to slow.
BackpropagationTrainer	BackpropagationTrainer.setL1Regularization(float regL1)	L1 regularization (sum of abs values) is used to prevent overfitting and too large weights.
BackpropagationTrainer	BackpropagationTrainer.setL2Regularization(float regL2)	L2 regularization (sum of squares) is used to prevent overfitting and too large weights.
BackpropagationTrainer	BackpropagationTrainer.setLearningRate(float learningRate)	Learning rate controls the step size as a percent of the error to use for adjusting internal parameters(weights) of the neural network.
BackpropagationTrainer	BackpropagationTrainer.setLearningRateDecay(float decayRate)	Learning rate decay lowers the learning rate with each epoch by devayRate factor, which may improve error lowering the error.
BackpropagationTrainer	BackpropagationTrainer.setMaxEpochs(long maxEpochs)	Deprecated. Use setStopEpochs instead
BackpropagationTrainer	BackpropagationTrainer.setMaxError(float maxError)	Deprecated. Use setStopError instead
BackpropagationTrainer	BackpropagationTrainer.setMomentum(float momentum)	Momentum settings helps to avoid oscillations in weight changes and get more stable and faster training.
BackpropagationTrainer	BackpropagationTrainer.setOptimizer(OptimizerType optimizer)
BackpropagationTrainer	BackpropagationTrainer.setShuffle(boolean shuffle)	Sets shuffle flag which determines if training set should be shuffled before each epoch.
BackpropagationTrainer	BackpropagationTrainer.setSnapshotPath(String snapshotPath)	Path to use for making snapshots - saving the current state of trained network during the training in order to be able to restore it from a training point.
BackpropagationTrainer	BackpropagationTrainer.setStopAccuracy(float stopAccuracy)
BackpropagationTrainer	BackpropagationTrainer.setStopEpochs(long stopEpochs)	Sets number of epochs/iterations to run the training.
BackpropagationTrainer	BackpropagationTrainer.setStopError(float stopError)	The training stops when/if training error reach this value.

Constructors in deepnetts.net.train with parameters of type BackpropagationTrainer

Modifier	Constructor	Description
	TrainingEvent(BackpropagationTrainer source, TrainingEvent.Type type)	Constructs a new TrainingEvent with specified source and type.