org.deeplearning4j.rbm

Class CRBM

java.lang.Object

org.deeplearning4j.nn.BaseNeuralNetwork

org.deeplearning4j.rbm.RBM

org.deeplearning4j.rbm.CRBM

All Implemented Interfaces:

Serializable, Cloneable, NeuralNetwork, Persistable, NeuralNetEpochListener

public class CRBM
extends RBM

Continuous Restricted Boltzmann Machine. Scale input to between 0 and 1. Note that data should be normalized to a 0 mean and unit variance. Consider each input unit as a probability of taking the value 1 with a different form of sampling. See: http://papers.nips.cc/paper/3048-greedy-layer-wise-training-of-deep-networks.pdf

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CRBM.Builder

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.NeuralNetwork

NeuralNetwork.LossFunction, NeuralNetwork.OptimizationAlgorithm

Field Summary

Fields inherited from class org.deeplearning4j.rbm.RBM

optimizer

Fields inherited from class org.deeplearning4j.nn.BaseNeuralNetwork

applySparsity, dist, doMask, dropOut, fanIn, firstTimeThrough, gradientListeners, hBias, hBiasAdaGrad, input, l2, lossFunction, momentum, nHidden, normalizeByInputRows, nVisible, optimizationAlgo, renderWeightsEveryNumEpochs, rng, sparsity, useAdaGrad, useRegularization, vBias, vBiasAdaGrad, W, wAdaGrad

Method Summary

Methods

Modifier and Type	Method and Description
org.jblas.DoubleMatrix	propDown(org.jblas.DoubleMatrix h) Calculates the activation of the hidden: h * W + vbias Note here that the visible unit returned here from the samples assumes zero mean and unit variance.
Pair<org.jblas.DoubleMatrix,org.jblas.DoubleMatrix>	sampleVisibleGivenHidden(org.jblas.DoubleMatrix h) Guess the visible values given the hidden

Methods inherited from class org.deeplearning4j.rbm.RBM

contrastiveDivergence, freeEnergy, getGradient, gibbhVh, lossFunction, propUp, reconstruct, sampleHiddenGivenVisible, train, trainTillConvergence, trainTillConvergence

Methods inherited from class org.deeplearning4j.nn.BaseNeuralNetwork

applyDropOutIfNecessary, applySparsity, clone, dropOut, epochDone, fanIn, getAdaGrad, getDist, getGradientListeners, gethBias, gethBiasAdaGrad, getInput, getL2, getLossFunction, getMomentum, getnHidden, getnVisible, getOptimizationAlgorithm, getReConstructionCrossEntropy, getRenderEpochs, getRng, getSparsity, getvBias, getVBiasAdaGrad, getW, hBiasMean, initWeights, jostleWeighMatrix, l2RegularizedCoefficient, load, lossFunction, merge, negativeLogLikelihood, negativeLoglikelihood, normalizeByInputRows, resetAdaGrad, setAdaGrad, setDist, setDropOut, setFanIn, setGradientListeners, sethBias, setHbiasAdaGrad, setInput, setL2, setLossFunction, setMomentum, setnHidden, setnVisible, setOptimizationAlgorithm, setRenderEpochs, setRng, setSparsity, setvBias, setVBiasAdaGrad, setW, squaredLoss, transpose, triggerGradientEvents, update, updateGradientAccordingToParams, write

Methods inherited from class java.lang.Object

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

Method Detail

propDown

public org.jblas.DoubleMatrix propDown(org.jblas.DoubleMatrix h)

Calculates the activation of the hidden: h * W + vbias Note here that the visible unit returned here from the samples assumes zero mean and unit variance.

Overrides:

propDown in class RBM

Parameters:

h - the hidden layer

Returns:

the approximated output of the hidden layer

sampleVisibleGivenHidden

public Pair<org.jblas.DoubleMatrix,org.jblas.DoubleMatrix> sampleVisibleGivenHidden(org.jblas.DoubleMatrix h)

Description copied from class: RBM

Guess the visible values given the hidden

Specified by:

sampleVisibleGivenHidden in interface NeuralNetwork

Overrides:

sampleVisibleGivenHidden in class RBM

Parameters:

h - the the hidden input

Returns:

a pair with mean, sample