package factored
 Alphabetic
 Public
 All
Type Members

case class
AbstractFactor
(variables: List[Variable[_]]) extends Product with Serializable
Abstract factors with no rows associated with variables.

class
ConstantDensityEstimator
extends DensityEstimator
A constant density estimator that always returns 1.0

abstract
class
DensityEstimator
extends AnyRef
The density estimator class is an abstract class to estimate the density of a point in some space given a list of weighted samples on that space.
The density estimator class is an abstract class to estimate the density of a point in some space given a list of weighted samples on that space. This class is principally used in Particle BP, where new samples for BP are generated from the estimate of the posterior. The density estimator is used in PBP to estimate densities during a MetropolisHastings sampler
 class DensityException extends RuntimeException

trait
DoubleDensityEstimator
extends DensityEstimator
Trait for Density estimators on the space of doubles

trait
FactoredAlgorithm
[T] extends Algorithm
Trait for algorithms that use factors.

trait
IntDensityEstimator
extends DensityEstimator
Trait for Density estimators on the space of ints

class
MPEVariableElimination
extends OneTimeMPE with ProbabilisticVariableElimination
Variable elimination algorithm to compute the most probable explanation.

class
ParticleGenerator
extends AnyRef
Class to handle sampling from continuous elements to make factors

class
ProbQueryVariableElimination
extends OneTimeProbQuery with ProbabilisticVariableElimination
Variable elimination algorithm that computes the conditional probability of query elements.

trait
ProbabilisticVariableElimination
extends VariableElimination[Double]
Variable elimination over probabilistic factors.

class
SufficientStatisticsVariableElimination
extends VariableElimination[(Double, Map[Parameter[_], Seq[Double]])]
Variable elimination for sufficient statistics factors.
Variable elimination for sufficient statistics factors. The final factor resulting from variable elimination contains a mapping of parameters to sufficient statistics vectors which can be used to maximize parameter values.

class
VEGraph
extends AnyRef
Induced graph for variable elimination.

trait
VariableElimination
[T] extends FactoredAlgorithm[T] with OneTime
Trait of algorithms that perform variable elimination.
Trait of algorithms that perform variable elimination.
 T
The type of entries in the factors.

case class
VariableInfo
(factors: Set[AbstractFactor], neighbors: Set[Variable[_]]) extends Product with Serializable
Information associated with a variable during variable elimination, including the factors to which it belongs and variables with which it shares a factor.
Information associated with a variable during variable elimination, including the factors to which it belongs and variables with which it shares a factor.
 factors
The abstract factors to which this variable belongs.
 neighbors
The variables that share a factor in common with this variable.
Value Members
 object MPEVariableElimination
 object ParticleGenerator
 object SufficientStatisticsVariableElimination
 object VEGraph
 object VariableElimination