org.deeplearning4j.nn.layers.convolution.subsampling

Class Subsampling1DLayer

java.lang.Object

org.deeplearning4j.nn.layers.BaseLayer<SubsamplingLayer>

org.deeplearning4j.nn.layers.convolution.subsampling.SubsamplingLayer

org.deeplearning4j.nn.layers.convolution.subsampling.Subsampling1DLayer

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Layer, Model

public class Subsampling1DLayer
extends SubsamplingLayer

1D (temporal) subsampling layer. Currently, we just subclass off the SubsamplingLayer and override the preOutput and backpropGradient methods. Specifically, since this layer accepts RNN (not CNN) InputTypes, we need to add a singleton fourth dimension before calling the respective superclass method, then remove it from the result. This approach treats a multivariate time series with L timesteps and P variables as an L x 1 x P image (L rows high, 1 column wide, P channels deep). The kernel should be H

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.api.Layer

Layer.TrainingMode, Layer.Type

Field Summary

Fields inherited from class org.deeplearning4j.nn.layers.convolution.subsampling.SubsamplingLayer

convolutionMode, helper

Fields inherited from class org.deeplearning4j.nn.layers.BaseLayer

conf, dropoutApplied, dropoutMask, gradient, gradientsFlattened, gradientViews, index, input, iterationListeners, maskArray, maskState, optimizer, params, paramsFlattened, score, solver

Constructor Summary

Constructors

Constructor and Description
Subsampling1DLayer(NeuralNetConfiguration conf)
Subsampling1DLayer(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray input)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training) Trigger an activation with the last specified input
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon) Calculate the gradient relative to the error in the next layer

Methods inherited from class org.deeplearning4j.nn.layers.convolution.subsampling.SubsamplingLayer

accumulateScore, activationMean, calcGradient, calcL1, calcL2, computeGradientAndScore, error, fit, fit, getParam, isPretrainLayer, iterate, merge, numParams, params, score, setParams, transpose, type, update

Methods inherited from class org.deeplearning4j.nn.layers.BaseLayer

activate, activate, activate, activate, activate, applyDropOutIfNecessary, applyLearningRateScoreDecay, applyMask, batchSize, clear, clone, conf, createGradient, derivativeActivation, feedForwardMaskArray, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, gradient, gradientAndScore, init, initParams, input, layerConf, layerNameAndIndex, numParams, paramTable, paramTable, preOutput, preOutput, preOutput, preOutput, setBackpropGradientsViewArray, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParamsViewArray, setParamTable, setScoreWithZ, toString, update, validateInput

Methods inherited from class java.lang.Object

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

Constructor Detail

Subsampling1DLayer

public Subsampling1DLayer(NeuralNetConfiguration conf)

Subsampling1DLayer

public Subsampling1DLayer(NeuralNetConfiguration conf,
                          org.nd4j.linalg.api.ndarray.INDArray input)

Method Detail

backpropGradient

public Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray> backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)

Description copied from interface: Layer

Calculate the gradient relative to the error in the next layer

Specified by:

backpropGradient in interface Layer

Overrides:

backpropGradient in class SubsamplingLayer

Parameters:

epsilon - w^(L+1)*delta^(L+1). Or, equiv: dC/da, i.e., (dC/dz)*(dz/da) = dC/da, where C is cost function a=sigma(z) is activation.

Returns:

Pair where Gradient is gradient for this layer, INDArray is epsilon needed by next layer, but before element-wise multiply by sigmaPrime(z). So for standard feed-forward layer, if this layer is L, then return.getSecond() == (w^(L)*(delta^(L))^T)^T

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(boolean training)

Description copied from interface: Layer

Trigger an activation with the last specified input

Specified by:

activate in interface Layer

Overrides:

activate in class SubsamplingLayer

Parameters:

training - training or test mode

Returns:

the activation of the last specified input