org.deeplearning4j.rbm

Class GaussianRectifiedLinearRBM

java.lang.Object

org.deeplearning4j.nn.BaseNeuralNetwork

org.deeplearning4j.rbm.RBM

org.deeplearning4j.rbm.GaussianRectifiedLinearRBM

All Implemented Interfaces:

Serializable, Cloneable, NeuralNetwork, Persistable, NeuralNetEpochListener

public class GaussianRectifiedLinearRBM
extends RBM

Visible units with gaussian noise and hidden binary activations. Meant for continuous data

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	GaussianRectifiedLinearRBM.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 Compute the mean activation of the visibles given hidden unit configurations for a set of training examples.
org.jblas.DoubleMatrix	propUp(org.jblas.DoubleMatrix v) Calculates the activation of the visible : sigmoid(v * W + hbias) Compute the mean activation of the hiddens given visible unit configurations for a set of training examples.
Pair<org.jblas.DoubleMatrix,org.jblas.DoubleMatrix>	sampleHiddenGivenVisible(org.jblas.DoubleMatrix v) Rectified linear units for output
Pair<org.jblas.DoubleMatrix,org.jblas.DoubleMatrix>	sampleVisibleGivenHidden(org.jblas.DoubleMatrix h) Guess the visible values given the hidden
void	trainTillConvergence(double learningRate, int k, org.jblas.DoubleMatrix input) Trains till global minimum is found.

Methods inherited from class org.deeplearning4j.rbm.RBM

contrastiveDivergence, freeEnergy, getGradient, gibbhVh, lossFunction, reconstruct, train, 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

trainTillConvergence

public void trainTillConvergence(double learningRate,
                        int k,
                        org.jblas.DoubleMatrix input)

Trains till global minimum is found.

Overrides:

trainTillConvergence in class RBM

Parameters:

learningRate -

k -

input -

propUp

public org.jblas.DoubleMatrix propUp(org.jblas.DoubleMatrix v)

Calculates the activation of the visible : sigmoid(v * W + hbias) Compute the mean activation of the hiddens given visible unit configurations for a set of training examples. Parameters

Overrides:

propUp in class RBM

Parameters:

v - the visible layer

Returns:

the approximated activations of the visible layer

sampleHiddenGivenVisible

public Pair<org.jblas.DoubleMatrix,org.jblas.DoubleMatrix> sampleHiddenGivenVisible(org.jblas.DoubleMatrix v)

Rectified linear units for output

Specified by:

sampleHiddenGivenVisible in interface NeuralNetwork

Overrides:

sampleHiddenGivenVisible in class RBM

Parameters:

v - the visible values

Returns:

a binomial distribution containing the expected values and the samples

propDown

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

Calculates the activation of the hidden: h * W + vbias Compute the mean activation of the visibles given hidden unit configurations for a set of training examples. Parameters

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