org.deeplearning4j.sda

Class DenoisingAutoEncoderOptimizer

java.lang.Object

org.deeplearning4j.optimize.NeuralNetworkOptimizer

org.deeplearning4j.sda.DenoisingAutoEncoderOptimizer

All Implemented Interfaces:

cc.mallet.optimize.Optimizable, cc.mallet.optimize.Optimizable.ByGradientValue, Serializable, NeuralNetEpochListener, OptimizableByGradientValueMatrix

public class DenoisingAutoEncoderOptimizer
extends NeuralNetworkOptimizer

Optimizes a denoising auto encoder. Handles DA specific parameters such as corruption level

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface cc.mallet.optimize.Optimizable

cc.mallet.optimize.Optimizable.ByBatchGradient, cc.mallet.optimize.Optimizable.ByCombiningBatchGradient, cc.mallet.optimize.Optimizable.ByGISUpdate, cc.mallet.optimize.Optimizable.ByGradient, cc.mallet.optimize.Optimizable.ByGradientValue, cc.mallet.optimize.Optimizable.ByHessian, cc.mallet.optimize.Optimizable.ByValue, cc.mallet.optimize.Optimizable.ByVotedPerceptron

Field Summary

Fields inherited from class org.deeplearning4j.optimize.NeuralNetworkOptimizer

errors, extraParams, log, lossFunction, lr, minLearningRate, network, opt, optimizationAlgorithm, tolerance

Constructor Summary

Constructors

Constructor and Description
DenoisingAutoEncoderOptimizer(BaseNeuralNetwork network, double lr, Object[] trainingParams, NeuralNetwork.OptimizationAlgorithm optimizationAlgorithm, NeuralNetwork.LossFunction lossFunction)

Method Summary

Methods

Modifier and Type	Method and Description
void	getValueGradient(double[] buffer)

Methods inherited from class org.deeplearning4j.optimize.NeuralNetworkOptimizer

epochDone, getErrors, getNumParameters, getParameter, getParameters, getParameters, getTolerance, getValue, getValueGradient, setParameter, setParameters, setParameters, setTolerance, train

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

DenoisingAutoEncoderOptimizer

public DenoisingAutoEncoderOptimizer(BaseNeuralNetwork network,
                             double lr,
                             Object[] trainingParams,
                             NeuralNetwork.OptimizationAlgorithm optimizationAlgorithm,
                             NeuralNetwork.LossFunction lossFunction)

Method Detail

getValueGradient

public void getValueGradient(double[] buffer)

Specified by:

getValueGradient in interface cc.mallet.optimize.Optimizable.ByGradientValue

Specified by:

getValueGradient in class NeuralNetworkOptimizer