org.deeplearning4j.models.rntn

Class RNTN

java.lang.Object

org.deeplearning4j.models.rntn.RNTN

All Implemented Interfaces:

Serializable

public class RNTN
extends Object
implements Serializable

Recursive Neural INDArray Network by Socher et. al This is a modified implementation of the sentiment analysis RNTN from Stanford that is intended to work with more general purpose inputs (scene detection with images, labeling series of sentences, among others) This implementation will also be faster in terms of parallelization as well as integration with native matrices/GPUs

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	RNTN.Builder

Field Summary

Fields

Modifier and Type	Field and Description
protected org.nd4j.linalg.api.activation.ActivationFunction	activationFunction
protected org.nd4j.linalg.api.activation.ActivationFunction	outputActivation
protected org.nd4j.linalg.learning.AdaGrad	paramAdaGrad
static String	UNKNOWN_FEATURE
protected double	value

Method Summary

Modifier and Type	Method and Description
String	basicCategory(String category)
void	fit(List<Tree> trainingBatch) Trains the network on this mini batch
void	forwardPropagateTree(Tree tree) This is the method to call for assigning labels and node vectors to the Tree.
org.nd4j.linalg.api.ndarray.INDArray	getBinaryClassification(String left, String right)
org.nd4j.linalg.api.ndarray.INDArray	getBinaryINDArray(String left, String right)
org.nd4j.linalg.api.ndarray.INDArray	getBinaryTransform(String left, String right)
org.nd4j.linalg.api.ndarray.INDArray	getClassWForNode(Tree node)
org.nd4j.linalg.api.ndarray.INDArray	getFeatureVector(String word)
org.nd4j.linalg.api.ndarray.INDArray	getINDArrayForNode(Tree node)
int	getNumParameters()
org.nd4j.linalg.api.ndarray.INDArray	getParameters()
org.nd4j.linalg.api.ndarray.INDArray	getUnaryClassification(String category)
double	getValue()
org.nd4j.linalg.api.ndarray.INDArray	getValueGradient(int iterations)
String	getVocabWord(String word)
org.nd4j.linalg.api.ndarray.INDArray	getWForNode(Tree node)
List<org.nd4j.linalg.api.ndarray.INDArray>	output(List<Tree> trees) output the prediction probabilities for each tree
List<Integer>	predict(List<Tree> trees) output the top level labels for each tree
org.nd4j.linalg.api.ndarray.INDArray	randomTransformBlock()
org.nd4j.linalg.api.ndarray.INDArray	randomTransformMatrix()
void	setParameters(org.nd4j.linalg.api.ndarray.INDArray params)
void	setParams(org.nd4j.linalg.api.ndarray.INDArray theta, Iterator<? extends org.nd4j.linalg.api.ndarray.INDArray>... matrices) Given a sequence of Iterators over a applyTransformToDestination of matrices, fill in all of the matrices with the entries in the theta vector.

Methods inherited from class java.lang.Object

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

Field Detail

value

protected double value

UNKNOWN_FEATURE

public static final String UNKNOWN_FEATURE

See Also:

Constant Field Values

activationFunction

protected org.nd4j.linalg.api.activation.ActivationFunction activationFunction

outputActivation

protected org.nd4j.linalg.api.activation.ActivationFunction outputActivation

paramAdaGrad

protected org.nd4j.linalg.learning.AdaGrad paramAdaGrad

Method Detail

randomTransformMatrix

public org.nd4j.linalg.api.ndarray.INDArray randomTransformMatrix()

randomTransformBlock

public org.nd4j.linalg.api.ndarray.INDArray randomTransformBlock()

fit

public void fit(List<Tree> trainingBatch)

Trains the network on this mini batch

Parameters:

trainingBatch - the trees to iterate on

setParams

public void setParams(org.nd4j.linalg.api.ndarray.INDArray theta,
                      Iterator<? extends org.nd4j.linalg.api.ndarray.INDArray>... matrices)

Given a sequence of Iterators over a applyTransformToDestination of matrices, fill in all of the matrices with the entries in the theta vector. Errors are thrown if the theta vector does not exactly fill the matrices.

getWForNode

public org.nd4j.linalg.api.ndarray.INDArray getWForNode(Tree node)

getINDArrayForNode

public org.nd4j.linalg.api.ndarray.INDArray getINDArrayForNode(Tree node)

getClassWForNode

public org.nd4j.linalg.api.ndarray.INDArray getClassWForNode(Tree node)

getFeatureVector

public org.nd4j.linalg.api.ndarray.INDArray getFeatureVector(String word)

getVocabWord

public String getVocabWord(String word)

basicCategory

public String basicCategory(String category)

getUnaryClassification

public org.nd4j.linalg.api.ndarray.INDArray getUnaryClassification(String category)

getBinaryClassification

public org.nd4j.linalg.api.ndarray.INDArray getBinaryClassification(String left,
                                                                    String right)

getBinaryTransform

public org.nd4j.linalg.api.ndarray.INDArray getBinaryTransform(String left,
                                                               String right)

getBinaryINDArray

public org.nd4j.linalg.api.ndarray.INDArray getBinaryINDArray(String left,
                                                              String right)

getNumParameters

public int getNumParameters()

getParameters

public org.nd4j.linalg.api.ndarray.INDArray getParameters()

forwardPropagateTree

public void forwardPropagateTree(Tree tree)

This is the method to call for assigning labels and node vectors to the Tree. After calling this, each of the non-leaf nodes will have the node vector and the predictions of their classes assigned to that subtree's node.

output

public List<org.nd4j.linalg.api.ndarray.INDArray> output(List<Tree> trees)

output the prediction probabilities for each tree

Parameters:

trees - the trees to predict

Returns:

the prediction probabilities for each tree

predict

public List<Integer> predict(List<Tree> trees)

output the top level labels for each tree

Parameters:

trees - the trees to predict

Returns:

the prediction labels for each tree

setParameters

public void setParameters(org.nd4j.linalg.api.ndarray.INDArray params)

getValueGradient

public org.nd4j.linalg.api.ndarray.INDArray getValueGradient(int iterations)

getValue

public double getValue()