org.deeplearning4j.nn.api

Interface Layer

All Superinterfaces:

Cloneable, Model, Serializable

All Known Implementing Classes:

AutoEncoder, BaseLayer, BasePretrainNetwork, ConvolutionDownSampleLayer, LSTM, OutputLayer, RBM, RecursiveAutoEncoder

public interface Layer
extends Serializable, Cloneable, Model

Interface for a layer of a neural network. This has an activation function, an input and output size, weights, and a bias

Author:

Adam Gibson

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate() Trigger an activation with the last specified input
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input) Initialize the layer with the given input and return the activation for this layer given this input
org.nd4j.linalg.api.ndarray.INDArray	activationMean()
Layer	clone()
NeuralNetConfiguration	conf() The configuration for the neural network
org.nd4j.linalg.api.ndarray.INDArray	getInput()
org.nd4j.linalg.api.ndarray.INDArray	getParam(String param) Get the parameter
void	initParams() Initialize the parameters
void	merge(Layer layer, int batchSize) Parameter averaging
Map<String,org.nd4j.linalg.api.ndarray.INDArray>	paramTable() The param table
org.nd4j.linalg.api.ndarray.INDArray	preOutput(org.nd4j.linalg.api.ndarray.INDArray x)
void	setConfiguration(NeuralNetConfiguration conf)
void	setInput(org.nd4j.linalg.api.ndarray.INDArray input)
void	setParam(String key, org.nd4j.linalg.api.ndarray.INDArray val) Set the parameter with a new ndarray
void	setParamTable(Map<String,org.nd4j.linalg.api.ndarray.INDArray> paramTable)
Layer	transpose() Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)

Methods inherited from interface org.deeplearning4j.nn.api.Model

batchSize, fit, fit, getGradient, gradientAndScore, input, iterate, numParams, params, score, setConf, setParams, transform, update, validateInput

Method Detail

merge

void merge(Layer layer,
           int batchSize)

Parameter averaging

Parameters:

layer - the layer to merge

batchSize - the batch size to merge on

getParam

org.nd4j.linalg.api.ndarray.INDArray getParam(String param)

Get the parameter

Parameters:

param - the key of the parameter

Returns:

the parameter vector/matrix with that particular key

initParams

void initParams()

Initialize the parameters

paramTable

Map<String,org.nd4j.linalg.api.ndarray.INDArray> paramTable()

The param table

Returns:

setParamTable

void setParamTable(Map<String,org.nd4j.linalg.api.ndarray.INDArray> paramTable)

setParam

void setParam(String key,
              org.nd4j.linalg.api.ndarray.INDArray val)

Set the parameter with a new ndarray

Parameters:

key - the key to se t

val - the new ndarray

activationMean

org.nd4j.linalg.api.ndarray.INDArray activationMean()

conf

NeuralNetConfiguration conf()

Description copied from interface: Model

The configuration for the neural network

Specified by:

conf in interface Model

Returns:

the configuration for the neural network

setConfiguration

void setConfiguration(NeuralNetConfiguration conf)

getInput

org.nd4j.linalg.api.ndarray.INDArray getInput()

setInput

void setInput(org.nd4j.linalg.api.ndarray.INDArray input)

preOutput

org.nd4j.linalg.api.ndarray.INDArray preOutput(org.nd4j.linalg.api.ndarray.INDArray x)

activate

org.nd4j.linalg.api.ndarray.INDArray activate()

Trigger an activation with the last specified input

Returns:

the activation of the last specified input

activate

org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input)

Initialize the layer with the given input and return the activation for this layer given this input

Parameters:

input - the input to use

Returns:

transpose

Layer transpose()

Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)

Returns:

the transposed layer

clone

Layer clone()