io.improbable.keanu.vertices.dbl.nonprobabilistic.operators.multiple

Class ReduceVertex

java.lang.Object

io.improbable.keanu.vertices.Vertex<DoubleTensor>

io.improbable.keanu.vertices.dbl.DoubleVertex

io.improbable.keanu.vertices.dbl.nonprobabilistic.operators.multiple.ReduceVertex

All Implemented Interfaces:

Variable<DoubleTensor,VertexState<DoubleTensor>>, io.improbable.keanu.kotlin.DoubleOperators<DoubleVertex>, io.improbable.keanu.kotlin.NumberOperators<DoubleVertex>, Differentiable, NonProbabilistic<DoubleTensor>, NonSaveableVertex, Observable<DoubleTensor>

public class ReduceVertex
extends DoubleVertex
implements Differentiable, NonProbabilistic<DoubleTensor>, NonSaveableVertex

Constructor Summary

Constructors

Constructor and Description
ReduceVertex(java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction, java.util.function.Supplier<PartialDerivative> forwardModeAutoDiffLambda, java.util.function.Function<PartialDerivative,java.util.Map<Vertex,PartialDerivative>> reverseModeAutoDiffLambda, Vertex<DoubleTensor>... input) Reduce vertex that assumes shape as inputs
ReduceVertex(java.util.List<? extends Vertex<DoubleTensor>> inputs, java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction) Reduce vertex that assumes shape as inputs
ReduceVertex(long[] shape, java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction, java.util.function.Supplier<PartialDerivative> forwardModeAutoDiffLambda, java.util.function.Function<PartialDerivative,java.util.Map<Vertex,PartialDerivative>> reverseModeAutoDiffLambda, Vertex<DoubleTensor>... input)
ReduceVertex(long[] shape, java.util.Collection<? extends Vertex<DoubleTensor>> inputs, java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction)
ReduceVertex(long[] shape, java.util.Collection<? extends Vertex<DoubleTensor>> inputs, java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction, java.util.function.Supplier<PartialDerivative> forwardModeAutoDiffLambda, java.util.function.Function<PartialDerivative,java.util.Map<Vertex,PartialDerivative>> reverseModeAutoDiffLambda)

Method Summary

Modifier and Type	Method and Description
DoubleTensor	calculate()
PartialDerivative	forwardModeAutoDifferentiation(java.util.Map<Vertex,PartialDerivative> derivativeOfParentsWithRespectToInput)
java.util.Map<Vertex,PartialDerivative>	reverseModeAutoDifferentiation(PartialDerivative derivativeOfOutputWithRespectToSelf)

Methods inherited from class io.improbable.keanu.vertices.dbl.DoubleVertex

abs, acos, asin, atan, atan2, ceil, concat, cos, div, div, divideBy, divideBy, equalTo, exp, floor, getValue, greaterThan, greaterThanOrEqualTo, lambda, lambda, lessThan, lessThanOrEqualTo, loadValue, log, logGamma, matrixDeterminant, matrixInverse, matrixMultiply, max, min, minus, minus, multiply, multiply, notEqualTo, observe, observe, permute, plus, plus, pow, pow, reshape, reverseDiv, reverseMinus, round, saveValue, setAndCascade, setAndCascade, setValue, setValue, setWithMask, setWithMask, sigmoid, sin, slice, sum, sum, take, tan, times, times, toGreaterThanMask, toGreaterThanMask, toGreaterThanOrEqualToMask, toGreaterThanOrEqualToMask, toInteger, toLessThanMask, toLessThanMask, toLessThanOrEqualToMask, toLessThanOrEqualToMask, transpose, unaryMinus

Methods inherited from class io.improbable.keanu.vertices.Vertex

addChild, addParent, addParents, equals, eval, getChildren, getConnectedGraph, getDegree, getId, getIndentation, getLabel, getObservedValue, getParents, getRank, getReference, getShape, getState, getValue, hashCode, hasValue, isDifferentiable, isObserved, isProbabilistic, lazyEval, observe, observeOwnValue, print, print, removeLabel, save, setAndCascade, setLabel, setLabel, setParents, setParents, setState, setValue, toString, unobserve

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface io.improbable.keanu.vertices.dbl.Differentiable

withRespectToSelf

Methods inherited from interface io.improbable.keanu.vertices.NonProbabilistic

contradictsObservation

Methods inherited from interface io.improbable.keanu.vertices.Observable

getObservedValue, isObserved, observe, unobserve

Constructor Detail

ReduceVertex

public ReduceVertex(long[] shape,
                    java.util.Collection<? extends Vertex<DoubleTensor>> inputs,
                    java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction,
                    java.util.function.Supplier<PartialDerivative> forwardModeAutoDiffLambda,
                    java.util.function.Function<PartialDerivative,java.util.Map<Vertex,PartialDerivative>> reverseModeAutoDiffLambda)

ReduceVertex

public ReduceVertex(long[] shape,
                    java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction,
                    java.util.function.Supplier<PartialDerivative> forwardModeAutoDiffLambda,
                    java.util.function.Function<PartialDerivative,java.util.Map<Vertex,PartialDerivative>> reverseModeAutoDiffLambda,
                    Vertex<DoubleTensor>... input)

ReduceVertex

public ReduceVertex(long[] shape,
                    java.util.Collection<? extends Vertex<DoubleTensor>> inputs,
                    java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction)

ReduceVertex

public ReduceVertex(java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction,
                    java.util.function.Supplier<PartialDerivative> forwardModeAutoDiffLambda,
                    java.util.function.Function<PartialDerivative,java.util.Map<Vertex,PartialDerivative>> reverseModeAutoDiffLambda,
                    Vertex<DoubleTensor>... input)

Reduce vertex that assumes shape as inputs

Parameters:

reduceFunction - reduce function

forwardModeAutoDiffLambda - auto diff supplier

reverseModeAutoDiffLambda - function for returning diff

input - input vertices to reduce

ReduceVertex

public ReduceVertex(java.util.List<? extends Vertex<DoubleTensor>> inputs,
                    java.util.function.BiFunction<DoubleTensor,DoubleTensor,DoubleTensor> reduceFunction)

Reduce vertex that assumes shape as inputs

Parameters:

reduceFunction - reduce function

inputs - input vertices to reduce

Method Detail

calculate

public DoubleTensor calculate()

Specified by:

calculate in interface NonProbabilistic<DoubleTensor>

forwardModeAutoDifferentiation

public PartialDerivative forwardModeAutoDifferentiation(java.util.Map<Vertex,PartialDerivative> derivativeOfParentsWithRespectToInput)

Specified by:

forwardModeAutoDifferentiation in interface Differentiable

reverseModeAutoDifferentiation

public java.util.Map<Vertex,PartialDerivative> reverseModeAutoDifferentiation(PartialDerivative derivativeOfOutputWithRespectToSelf)

Specified by:

reverseModeAutoDifferentiation in interface Differentiable