org.nd4j.linalg.api.ops.impl.accum

Class Bias

java.lang.Object

org.nd4j.linalg.api.ops.BaseOp

org.nd4j.linalg.api.ops.BaseAccumulation

org.nd4j.linalg.api.ops.impl.accum.Bias

All Implemented Interfaces:

Accumulation, Op

public class Bias
extends BaseAccumulation

Calculate a bias

Author:

Adam Gibson

Field Summary

Fields inherited from class org.nd4j.linalg.api.ops.BaseAccumulation

applyFinalTransform, finalResult, finalResultComplex

Fields inherited from class org.nd4j.linalg.api.ops.BaseOp

extraArgs, n, numProcessed, passThrough, x, y, z

Constructor Summary

Constructors

Constructor and Description
Bias()
Bias(INDArray x)
Bias(INDArray x, INDArray y)
Bias(INDArray x, INDArray y, INDArray z, int n)
Bias(INDArray x, INDArray y, int n)

Method Summary

Modifier and Type	Method and Description
double	combineSubResults(double first, double second) Combine sub-results, when the Accumulation operation is split and executed in parallel. Sometimes this is the same as the update operation (i.e., in sum operation), but often it is not (for example, in L2 norm, sqrt(1/n * sum_i x_i^2).
float	combineSubResults(float first, float second)
IComplexNumber	combineSubResults(IComplexNumber first, IComplexNumber second)
void	exec() Execute the op if its pass through (not needed most of the time)
void	exec(int... dimension) Exec along each dimension
void	init(INDArray x, INDArray y, INDArray z, int n) Initialize the operation based on the parameters
String	name() The name of this operation
double	op(double origin) Transform an individual element
float	op(float origin) Transform an individual element
IComplexNumber	op(IComplexNumber origin) Transform an individual element
Op	opForDimension(int index, int... dimension) A copy of this operation for a particular dimension of the input
Op	opForDimension(int index, int dimension) A copy of this operation for a particular dimension of the input
double	update(double accum, double x) Do one accumulation update for a single-argument accumulation, given the current accumulation value and another value to be processed/accumulated
double	update(double accum, double x, double y) Do an accumulation update for a pair-wise (op(x,y)) accumulation, given the current accumulation value and a pair of values to be processed/accumulated
float	update(float accum, float x)
float	update(float accum, float x, float y)
IComplexNumber	update(IComplexNumber accum, double x) Complex update.
IComplexNumber	update(IComplexNumber accum, double x, double y) Complex update.
IComplexNumber	update(IComplexNumber accum, IComplexNumber x) Complex update.
IComplexNumber	update(IComplexNumber accum, IComplexNumber x, double y) Complex update.
IComplexNumber	update(IComplexNumber accum, IComplexNumber x, IComplexNumber y) Complex update.
IComplexNumber	zeroComplex() Complex initial value

Methods inherited from class org.nd4j.linalg.api.ops.BaseAccumulation

applyFinalTransform, calculateFinalResult, calculateFinalResult, currentResult, getAndSetFinalResult, getAndSetFinalResult, getAndSetFinalResult, getFinalResult, getFinalResultComplex, numProcessed, op, op, op, op, op, setApplyFinalTransform, setFinalResult, setFinalResultComplex, zeroDouble, zeroFloat

Methods inherited from class org.nd4j.linalg.api.ops.BaseOp

ensureProperVectors, extraArgs, isPassThrough, n, setN, setX, setY, setZ, toString, x, y, z

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.nd4j.linalg.api.ops.Op

extraArgs, isPassThrough, n, setN, setX, setY, setZ, x, y, z

Constructor Detail

Bias

public Bias()

Bias

public Bias(INDArray x,
            INDArray y,
            INDArray z,
            int n)

Bias

public Bias(INDArray x,
            INDArray y,
            int n)

Bias

public Bias(INDArray x)

Bias

public Bias(INDArray x,
            INDArray y)

Method Detail

name

public String name()

Description copied from interface: Op

The name of this operation

Returns:

the name of this operation

opForDimension

public Op opForDimension(int index,
                         int dimension)

Description copied from interface: Op

A copy of this operation for a particular dimension of the input

Parameters:

index - the index of the op to iterate over

dimension - the dimension to ge the input for

Returns:

the operation for that dimension

opForDimension

public Op opForDimension(int index,
                         int... dimension)

Description copied from interface: Op

A copy of this operation for a particular dimension of the input

Parameters:

index - the index of the op to iterate over

dimension - the dimension to ge the input for

Returns:

the operation for that dimension

op

public IComplexNumber op(IComplexNumber origin)

Description copied from interface: Op

Transform an individual element

Specified by:

op in interface Op

Overrides:

op in class BaseAccumulation

Parameters:

origin - the origin element

Returns:

the new element

op

public double op(double origin)

Description copied from interface: Op

Transform an individual element

Specified by:

op in interface Op

Overrides:

op in class BaseAccumulation

Parameters:

origin - the origin element

Returns:

the new element

op

public float op(float origin)

Description copied from interface: Op

Transform an individual element

Specified by:

op in interface Op

Overrides:

op in class BaseAccumulation

Parameters:

origin - the origin element

Returns:

the new element

update

public double update(double accum,
                     double x)

Description copied from interface: Accumulation

Do one accumulation update for a single-argument accumulation, given the current accumulation value and another value to be processed/accumulated

Parameters:

accum - The current accumulation value

x - The next/new value to be processed/accumulated

Returns:

The updated accumulation value

update

public double update(double accum,
                     double x,
                     double y)

Description copied from interface: Accumulation

Do an accumulation update for a pair-wise (op(x,y)) accumulation, given the current accumulation value and a pair of values to be processed/accumulated

Parameters:

accum - The current accumulation value

x - The next/new x value to be processed/accumulated

y - The next/new y value to be processed/accumulated

Returns:

the updated accumulation value

update

public float update(float accum,
                    float x)

See Also:

Accumulation.update(double, double)

update

public float update(float accum,
                    float x,
                    float y)

See Also:

Accumulation.update(double, double, double)

update

public IComplexNumber update(IComplexNumber accum,
                             double x)

Description copied from interface: Accumulation

Complex update.

See Also:

Accumulation.update(double, double)

update

public IComplexNumber update(IComplexNumber accum,
                             double x,
                             double y)

Description copied from interface: Accumulation

Complex update.

See Also:

Accumulation.update(double, double, double)

update

public IComplexNumber update(IComplexNumber accum,
                             IComplexNumber x)

Description copied from interface: Accumulation

Complex update.

See Also:

Accumulation.update(double, double)

update

public IComplexNumber update(IComplexNumber accum,
                             IComplexNumber x,
                             IComplexNumber y)

Description copied from interface: Accumulation

Complex update.

See Also:

Accumulation.update(double, double, double)

update

public IComplexNumber update(IComplexNumber accum,
                             IComplexNumber x,
                             double y)

Description copied from interface: Accumulation

Complex update.

See Also:

Accumulation.update(double, double, double)

zeroComplex

public IComplexNumber zeroComplex()

Description copied from interface: Accumulation

Complex initial value

Specified by:

zeroComplex in interface Accumulation

Overrides:

zeroComplex in class BaseAccumulation

Returns:

the complex initial value

init

public void init(INDArray x,
                 INDArray y,
                 INDArray z,
                 int n)

Description copied from interface: Op

Initialize the operation based on the parameters

Specified by:

init in interface Op

Overrides:

init in class BaseAccumulation

Parameters:

x - the input

y - the pairwise transform ndarray

z - the resulting ndarray

n - the number of elements

combineSubResults

public double combineSubResults(double first,
                                double second)

Description copied from interface: Accumulation

Combine sub-results, when the Accumulation operation is split and executed in parallel.
Sometimes this is the same as the update operation (i.e., in sum operation), but often it is not (for example, in L2 norm, sqrt(1/n * sum_i x_i^2).

Specified by:

combineSubResults in interface Accumulation

Overrides:

combineSubResults in class BaseAccumulation

Parameters:

first - The first sub-value to be combined

second - The second sub-value to be combined

Returns:

The combined result

combineSubResults

public float combineSubResults(float first,
                               float second)

Specified by:

combineSubResults in interface Accumulation

Overrides:

combineSubResults in class BaseAccumulation

See Also:

Accumulation.combineSubResults(double, double)

combineSubResults

public IComplexNumber combineSubResults(IComplexNumber first,
                                        IComplexNumber second)

Specified by:

combineSubResults in interface Accumulation

Overrides:

combineSubResults in class BaseAccumulation

See Also:

Accumulation.combineSubResults(double, double)

exec

public void exec()

Description copied from interface: Op

Execute the op if its pass through (not needed most of the time)

Specified by:

exec in interface Op

Overrides:

exec in class BaseOp

exec

public void exec(int... dimension)

Description copied from interface: Op

Exec along each dimension

Specified by:

exec in interface Op

Overrides:

exec in class BaseOp

Parameters:

dimension - the dimensions to execute on