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

public class CRBM
extends RBM

Continuous Restricted Boltzmann Machine

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CRBM.Builder

Field Summary

Fields inherited from class org.deeplearning4j.rbm.RBM

optimizer

Fields inherited from class org.deeplearning4j.nn.BaseNeuralNetwork

dist, fanIn, hBias, input, l2, momentum, nHidden, nVisible, renderWeightsEveryNumEpochs, rng, sparsity, useRegularization, vBias, W

Constructor Summary

Constructors

Constructor and Description
CRBM()
CRBM(org.jblas.DoubleMatrix input, int n_visible, int n_hidden, org.jblas.DoubleMatrix W, org.jblas.DoubleMatrix hbias, org.jblas.DoubleMatrix vbias, org.apache.commons.math3.random.RandomGenerator rng, double fanIn, org.apache.commons.math3.distribution.RealDistribution dist)
CRBM(int nVisible, int nHidden, org.jblas.DoubleMatrix W, org.jblas.DoubleMatrix hbias, org.jblas.DoubleMatrix vbias, org.apache.commons.math3.random.RandomGenerator rng, double fanIn, org.apache.commons.math3.distribution.RealDistribution dist)

Method Summary

Methods

Modifier and Type	Method and Description
org.jblas.DoubleMatrix	propDown(org.jblas.DoubleMatrix h) Propagates hidden down to visible
Pair<org.jblas.DoubleMatrix,org.jblas.DoubleMatrix>	sampleVGivenH(org.jblas.DoubleMatrix h) Guess the visible values given the hidden

Methods inherited from class org.deeplearning4j.rbm.RBM

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

Methods inherited from class org.deeplearning4j.nn.BaseNeuralNetwork

clone, fanIn, getDist, gethBias, getInput, getL2, getMomentum, getnHidden, getnVisible, getReConstructionCrossEntropy, getRenderEpochs, getRng, getSparsity, getvBias, getW, initWeights, jostleWeighMatrix, l2RegularizedCoefficient, load, lossFunction, merge, setDist, setFanIn, sethBias, setInput, setL2, setMomentum, setnHidden, setnVisible, setRenderEpochs, setRng, setSparsity, setvBias, setW, squaredLoss, transpose, update, write

Methods inherited from class java.lang.Object

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

Constructor Detail

CRBM

public CRBM()

CRBM

public CRBM(org.jblas.DoubleMatrix input,
    int n_visible,
    int n_hidden,
    org.jblas.DoubleMatrix W,
    org.jblas.DoubleMatrix hbias,
    org.jblas.DoubleMatrix vbias,
    org.apache.commons.math3.random.RandomGenerator rng,
    double fanIn,
    org.apache.commons.math3.distribution.RealDistribution dist)

CRBM

public CRBM(int nVisible,
    int nHidden,
    org.jblas.DoubleMatrix W,
    org.jblas.DoubleMatrix hbias,
    org.jblas.DoubleMatrix vbias,
    org.apache.commons.math3.random.RandomGenerator rng,
    double fanIn,
    org.apache.commons.math3.distribution.RealDistribution dist)

Method Detail

propDown

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

Description copied from class: RBM

Propagates hidden down to visible

Overrides:

propDown in class RBM

Parameters:

h - the hidden layer

Returns:

the approximated output of the hidden layer

sampleVGivenH

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

Description copied from class: RBM

Guess the visible values given the hidden

Overrides:

sampleVGivenH in class RBM

Returns: