mikera.vectorz

Class Op2

java.lang.Object

mikera.vectorz.Op2

Direct Known Subclasses:

Add, AddFunction, ComposedOp2, CrossEntropy, CrossEntropyDerivative, CrossEntropyLogisticDerivative, Max, Min

public abstract class Op2
extends Object

Abstract class for representing a unary operation

Author:

Mike

Constructor Summary

Constructors

Constructor and Description
Op2()

Method Summary

Modifier and Type	Method and Description
abstract double	apply(double x, double y)
void	applyTo(ADenseArrayVector a, AVector b)
void	applyTo(AMatrix a, AMatrix b)
void	applyTo(AScalar a, AScalar b)
void	applyTo(AVector a, AVector b)
void	applyTo(double[] data, AVector b)
void	applyTo(double[] data, double b)
void	applyTo(double[] data, int start, int length, AVector b)
void	applyTo(double[] data, int start, int length, double b)
void	applyTo(INDArray a, INDArray b)
double	averageValue()
void	constrainValues(double[] src, double[] dest, int offset, int length) Creates a copy of the values of src in dest, constraining them to be within the valid range of output values from this Op
Op2	getDerivative(int i) Gets the derivative of this Op2 with respect to the specified parameter (0 or 1)
boolean	isBounded()
boolean	isStochastic() Returns true if the operator is stochastic, i.e returns random values for at least some inputs
double	maxValue()
double	minValue()
double	reduce(double init, double[] data, int offset, int length) Method to reduce over a subset of a double[] array
double	reduce(double init, double[] data, int offset, int length, int stride) Method to reduce over a strided subset of a double[] array
double	reduceZeros(double init, long length) Method to reduce over a sequence of zeros.
double	reduceZeros(long length) Method to reduce over a sequence of zeros.
String	toString()
boolean	validateOutput(double[] output) Validates whether all values in a double[] are within the possible output range for this Op

Methods inherited from class java.lang.Object

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

Constructor Detail

Op2

public Op2()

Method Detail

apply

public abstract double apply(double x,
                             double y)

applyTo

public void applyTo(AVector a,
                    AVector b)

applyTo

public void applyTo(AMatrix a,
                    AMatrix b)

applyTo

public void applyTo(AScalar a,
                    AScalar b)

applyTo

public void applyTo(ADenseArrayVector a,
                    AVector b)

applyTo

public void applyTo(INDArray a,
                    INDArray b)

applyTo

public void applyTo(double[] data,
                    int start,
                    int length,
                    AVector b)

applyTo

public void applyTo(double[] data,
                    int start,
                    int length,
                    double b)

applyTo

public void applyTo(double[] data,
                    AVector b)

applyTo

public void applyTo(double[] data,
                    double b)

isStochastic

public boolean isStochastic()

Returns true if the operator is stochastic, i.e returns random values for at least some inputs

Returns:

averageValue

public double averageValue()

minValue

public double minValue()

maxValue

public double maxValue()

validateOutput

public boolean validateOutput(double[] output)

Validates whether all values in a double[] are within the possible output range for this Op

Parameters:

output -

Returns:

constrainValues

public void constrainValues(double[] src,
                            double[] dest,
                            int offset,
                            int length)

Creates a copy of the values of src in dest, constraining them to be within the valid range of output values from this Op

Parameters:

src -

dest -

offset -

length -

isBounded

public boolean isBounded()

toString

public String toString()

Overrides:

toString in class Object

reduce

public double reduce(double init,
                     double[] data,
                     int offset,
                     int length)

Method to reduce over a subset of a double[] array

reduce

public double reduce(double init,
                     double[] data,
                     int offset,
                     int length,
                     int stride)

Method to reduce over a strided subset of a double[] array

reduceZeros

public double reduceZeros(double init,
                          long length)

Method to reduce over a sequence of zeros. Optimises for common stable cases.

Parameters:

init -

length -

Returns:

reduceZeros

public double reduceZeros(long length)

Method to reduce over a sequence of zeros. Optimises for common stable cases.

Parameters:

length -

Returns:

getDerivative

public Op2 getDerivative(int i)

Gets the derivative of this Op2 with respect to the specified parameter (0 or 1)

Parameters:

i -

Returns: