org.deeplearning4j.nn

Class HiddenLayer

java.lang.Object

org.deeplearning4j.nn.HiddenLayer

All Implemented Interfaces:

Serializable

public class HiddenLayer
extends Object
implements Serializable

Vectorized Hidden Layer

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	HiddenLayer.Builder

Constructor Summary

Constructors

Constructor and Description
HiddenLayer(int nIn, int nOut, org.jblas.DoubleMatrix W, org.jblas.DoubleMatrix b, org.apache.commons.math3.random.RandomGenerator rng, org.jblas.DoubleMatrix input)
HiddenLayer(int nIn, int nOut, org.jblas.DoubleMatrix W, org.jblas.DoubleMatrix b, org.apache.commons.math3.random.RandomGenerator rng, org.jblas.DoubleMatrix input, ActivationFunction activationFunction)

Method Summary

Methods

Modifier and Type	Method and Description
org.jblas.DoubleMatrix	activate() Trigger an activation with the last specified input
org.jblas.DoubleMatrix	activate(org.jblas.DoubleMatrix input) Initialize the layer with the given input and return the activation for this layer given this input
HiddenLayer	clone()
ActivationFunction	getActivationFunction()
org.jblas.DoubleMatrix	getB()
org.jblas.DoubleMatrix	getInput()
int	getnIn()
int	getnOut()
org.apache.commons.math3.random.RandomGenerator	getRng()
org.jblas.DoubleMatrix	getW()
org.jblas.DoubleMatrix	sample_h_given_v() Sample this hidden layer given the last input.
org.jblas.DoubleMatrix	sampleHGivenV(org.jblas.DoubleMatrix input) Sample this hidden layer given the input and initialize this layer with the given input
void	setActivationFunction(ActivationFunction activationFunction)
void	setB(org.jblas.DoubleMatrix b)
void	setInput(org.jblas.DoubleMatrix input)
void	setnIn(int nIn)
void	setnOut(int nOut)
void	setRng(org.apache.commons.math3.random.RandomGenerator rng)
void	setW(org.jblas.DoubleMatrix w)
HiddenLayer	transpose()

Methods inherited from class java.lang.Object

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

Constructor Detail

HiddenLayer

public HiddenLayer(int nIn,
           int nOut,
           org.jblas.DoubleMatrix W,
           org.jblas.DoubleMatrix b,
           org.apache.commons.math3.random.RandomGenerator rng,
           org.jblas.DoubleMatrix input,
           ActivationFunction activationFunction)

HiddenLayer

public HiddenLayer(int nIn,
           int nOut,
           org.jblas.DoubleMatrix W,
           org.jblas.DoubleMatrix b,
           org.apache.commons.math3.random.RandomGenerator rng,
           org.jblas.DoubleMatrix input)

Method Detail

getnIn

public int getnIn()

setnIn

public void setnIn(int nIn)

getnOut

public int getnOut()

setnOut

public void setnOut(int nOut)

getW

public org.jblas.DoubleMatrix getW()

setW

public void setW(org.jblas.DoubleMatrix w)

getB

public org.jblas.DoubleMatrix getB()

setB

public void setB(org.jblas.DoubleMatrix b)

getRng

public org.apache.commons.math3.random.RandomGenerator getRng()

setRng

public void setRng(org.apache.commons.math3.random.RandomGenerator rng)

getInput

public org.jblas.DoubleMatrix getInput()

setInput

public void setInput(org.jblas.DoubleMatrix input)

getActivationFunction

public ActivationFunction getActivationFunction()

setActivationFunction

public void setActivationFunction(ActivationFunction activationFunction)

clone

public HiddenLayer clone()

Overrides:

clone in class Object

transpose

public HiddenLayer transpose()

activate

public org.jblas.DoubleMatrix activate()

Trigger an activation with the last specified input

Returns:

the activation of the last specified input

activate

public org.jblas.DoubleMatrix activate(org.jblas.DoubleMatrix 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:

sampleHGivenV

public org.jblas.DoubleMatrix sampleHGivenV(org.jblas.DoubleMatrix input)

Sample this hidden layer given the input and initialize this layer with the given input

Parameters:

input - the input to sample

Returns:

the activation for this layer given the input

sample_h_given_v

public org.jblas.DoubleMatrix sample_h_given_v()

Sample this hidden layer given the last input.

Returns:

the activation for this layer given the previous input