Modifier and Type | Class and Description |
---|---|
class |
InferenceApplication |
class |
LazyMPEInference
Performs MPE inference (see MPEInference), but does not require all ground atoms to be
specified ahead of time.
|
class |
MPEInference
Infers the most-probable explanation (MPE) state of the
RandomVariableAtoms persisted in a Database,
according to a
Model , given the Database's ObservedAtoms. |
Modifier and Type | Class and Description |
---|---|
class |
VotedPerceptron
Learns new weights for the weighted rules in a model using the voted perceptron algorithm.
|
class |
WeightLearningApplication
Abstract class for learning the weights of weighted mutableRules from data for a model.
|
Modifier and Type | Class and Description |
---|---|
class |
ExpectationMaximization
Abstract superclass for implementations of the expectation-maximization
algorithm for learning with latent variables.
|
class |
HardEM
EM algorithm which fits a point distribution to the single most probable
assignment of truth values to the latent variables during the E-step.
|
class |
PairedDualLearner
Learns the parameters of a HL-MRF with latent variables, using a maximum-likelihood
technique that interleaves updates of the parameters and inference steps for
fast training.
|
Modifier and Type | Class and Description |
---|---|
class |
LazyMaxLikelihoodMPE
Voted perception algorithm that does not require a ground model of pre-specified dimensionality.
|
class |
MaxLikelihoodMPE
Learns weights by optimizing the log likelihood of the data using
the voted perceptron algorithm.
|
class |
MaxPiecewisePseudoLikelihood
Learns weights by optimizing the piecewise-pseudo-log-likelihood of the data using
the voted perceptron algorithm.
|
class |
MaxPseudoLikelihood
Learns weights by optimizing the pseudo-log-likelihood of the data using
the voted perceptron algorithm.
|
Modifier and Type | Class and Description |
---|---|
class |
Hyperband
Hyperband.
|
class |
InitialWeightHyperband
Hyperband, but the weights chosen are used as initial weights for further weight learning.
|
Modifier and Type | Class and Description |
---|---|
class |
BaseGridSearch
The base for grid search-like method.
|
class |
ContinuousRandomGridSearch
A grid search that just randomly samples from a continuous grid [0, 1).
|
class |
GridSearch
An exhaustive grid search for weights.
|
class |
GuidedRandomGridSearch
Randomly search a some locations and then look around those locations.
|
class |
InitialWeightGridSearch
GridSearch over the initial weights and then run weight learning like normal.
|
class |
InitialWeightRandomGridSearch
Like InitialWeightGridSearch, but use random grid search instead of exhaustive.
|
class |
InitialWeightRankSearch
RankSearch over the initial weights and then run weight learning like normal.
|
class |
RandomGridSearch
A random grid search that searches a finite number of locations.
|
class |
RankSearch
A grid seach-like method that searchs over the possible rankings of rules.
|
Copyright © 2018 University of California, Santa Cruz. All rights reserved.