Uses of Interface
org.encog.neural.networks.training.Strategy

Packages that use Strategy

org.encog.neural.networks.training
org.encog.neural.networks.training.concurrent.jobs
org.encog.neural.networks.training.neat
org.encog.neural.networks.training.strategy
org.encog.neural.networks.training.strategy.end

Uses of Strategy in org.encog.neural.networks.training

Methods in org.encog.neural.networks.training that return types with arguments of type Strategy

List<Strategy>	Train.getStrategies()
List<Strategy>	BasicTraining.getStrategies()

Methods in org.encog.neural.networks.training with parameters of type Strategy

void	Train.addStrategy(Strategy strategy) Training strategies can be added to improve the training results.
void	BasicTraining.addStrategy(Strategy strategy) Training strategies can be added to improve the training results.

Uses of Strategy in org.encog.neural.networks.training.concurrent.jobs

Methods in org.encog.neural.networks.training.concurrent.jobs that return types with arguments of type Strategy

List<Strategy>

TrainingJob.getStrategies()

Uses of Strategy in org.encog.neural.networks.training.neat

Methods in org.encog.neural.networks.training.neat that return types with arguments of type Strategy

List<Strategy>

NEATTraining.getStrategies() Returns an empty list, strategies are not supported.

Methods in org.encog.neural.networks.training.neat with parameters of type Strategy

void	NEATTraining.addStrategy(Strategy strategy) Not supported, will throw an error.

Uses of Strategy in org.encog.neural.networks.training.strategy

Classes in org.encog.neural.networks.training.strategy that implement Strategy

class	Greedy A simple greedy strategy.
class	HybridStrategy A hybrid stragey allows a secondary training algorithm to be used.
class	RequiredImprovementStrategy The reset strategy will reset the weights if the neural network fails to improve by the specified amount over a number of cycles.
class	ResetStrategy The reset strategy will reset the weights if the neural network fails to fall below a specified error by a specified number of cycles.
class	SmartLearningRate Attempt to automatically set the learning rate in a learning method that supports a learning rate.
class	SmartMomentum Attempt to automatically set a momentum in a training algorithm that supports momentum.
class	StopTrainingStrategy This strategy will indicate once training is no longer improving the neural network by a specified amount, over a specified number of cycles.

Uses of Strategy in org.encog.neural.networks.training.strategy.end

Subinterfaces of Strategy in org.encog.neural.networks.training.strategy.end

interface

EndTrainingStrategy

Classes in org.encog.neural.networks.training.strategy.end that implement Strategy

class	EndIterationsStrategy
class	EndMaxErrorStrategy
class	EndMinutesStrategy