io.improbable.keanu

Class Keanu.Optimizer.Gradient

java.lang.Object

io.improbable.keanu.Keanu.Optimizer.Gradient

Enclosing class:

Keanu.Optimizer

public class Keanu.Optimizer.Gradient
extends java.lang.Object

Constructor Summary

Constructors

Constructor and Description
Gradient()

Method Summary

Modifier and Type	Method and Description
GradientOptimizer.GradientOptimizerBuilder	builderFor(BayesianNetwork network)
GradientOptimizer.GradientOptimizerBuilder	builderFor(java.util.Set<Vertex> connectedGraph)
GradientOptimizer	of(BayesianNetwork bayesNet) Creates a GradientOptimizer which provides methods for optimizing the values of latent variables of the Bayesian network to maximise probability.
GradientOptimizer	of(java.util.Collection<? extends Vertex> vertices) Creates a Bayesian network from the given vertices and uses this to create a GradientOptimizer.
GradientOptimizer	ofConnectedGraph(Vertex<?> vertexFromNetwork) Creates a Bayesian network from the graph connected to the given vertex and uses this to create a GradientOptimizer.

Methods inherited from class java.lang.Object

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

Constructor Detail

Gradient

public Gradient()

Method Detail

of

public GradientOptimizer of(BayesianNetwork bayesNet)

Creates a GradientOptimizer which provides methods for optimizing the values of latent variables of the Bayesian network to maximise probability.

Parameters:

bayesNet - The Bayesian network to run optimization on.

Returns:

a GradientOptimizer

of

public GradientOptimizer of(java.util.Collection<? extends Vertex> vertices)

Creates a Bayesian network from the given vertices and uses this to create a GradientOptimizer. This provides methods for optimizing the values of latent variables of the Bayesian network to maximise probability.

Parameters:

vertices - The vertices to create a Bayesian network from.

Returns:

a GradientOptimizer

ofConnectedGraph

public GradientOptimizer ofConnectedGraph(Vertex<?> vertexFromNetwork)

Creates a Bayesian network from the graph connected to the given vertex and uses this to create a GradientOptimizer. This provides methods for optimizing the values of latent variables of the Bayesian network to maximise probability.

Parameters:

vertexFromNetwork - A vertex in the graph to create the Bayesian network from

Returns:

a GradientOptimizer

builderFor

public GradientOptimizer.GradientOptimizerBuilder builderFor(java.util.Set<Vertex> connectedGraph)

builderFor

public GradientOptimizer.GradientOptimizerBuilder builderFor(BayesianNetwork network)