org.deeplearning4j.optimize.solvers.accumulation.encoding

Interface ThresholdAlgorithm

All Superinterfaces:

Serializable

All Known Implementing Classes:

AdaptiveThresholdAlgorithm, FixedThresholdAlgorithm, TargetSparsityThresholdAlgorithm

public interface ThresholdAlgorithm
extends Serializable

Method Summary

Modifier and Type	Method and Description
double	calculateThreshold(int iteration, int epoch, Double lastThreshold, Boolean lastWasDense, Double lastSparsityRatio, INDArray updatesPlusResidual)
ThresholdAlgorithm	clone()
ThresholdAlgorithmReducer	newReducer() Create a new ThresholdAlgorithmReducer.

Method Detail

calculateThreshold

double calculateThreshold(int iteration,
                          int epoch,
                          Double lastThreshold,
                          Boolean lastWasDense,
                          Double lastSparsityRatio,
                          INDArray updatesPlusResidual)

Parameters:

iteration - Current neural network training iteration

epoch - Current neural network training epoch

lastThreshold - The encoding threshold used in the last iteration - if available. May be null for first iteration in an epoch (where no 'last iteration' value is available)

lastWasDense - Whether the last encoding was dense (true) or sparse (false). May be null for the first iteration in an epoch (where no 'last iteration' value is available)

lastSparsityRatio - The sparsity ratio of the last iteration. Sparsity ratio is defined as numElements(encoded)/length(updates). A sparsity ratio of 1.0 would mean all entries present in encoded representation; a sparsity ratio of 0.0 would mean the encoded vector did not contain any values. Note: when the last encoding was dense, lastSparsityRatio is always null - this means that the sparsity ratio is larger than 1/16 = 0.0625

updatesPlusResidual - The actual array (updates plus residual) that will be encoded using the threshold calculated/returned by this method

Returns:

newReducer

ThresholdAlgorithmReducer newReducer()

Create a new ThresholdAlgorithmReducer. Note that implementations should NOT add the curret ThresholdAlgorithm to it.

Returns:

ThresholdAlgorithmReducer

clone

ThresholdAlgorithm clone()

Returns:

A clone of the current threshold algorithm