Package | Description |
---|---|
de.up.ling.irtg.learning_rates |
This package includes basic learning rates used for SGD algorithms.
|
de.up.ling.irtg.sampling.rule_weighting |
This package contains automata with adaptable sampling heuristics.
|
Modifier and Type | Class and Description |
---|---|
class |
AdaGrad
A simple implementation of the widely used AdaGrad learning rate.
|
Constructor and Description |
---|
AutomatonWeighted(TreeAutomaton basis,
int regularizationExponent,
double regularizationDivisor,
LearningRate rate)
Creates a new instance that weights trees according to the rule weights
from the given automaton and uses the automaton as the basis for sampling.
|
RegularizedKLRuleWeighting(TreeAutomaton basis,
int regularizationExponent,
double regularizationDivisor,
LearningRate rate)
Creates a new instance with the regularization given by the specified values.
|
Copyright © 2017. All rights reserved.