Modifier and Type | Method and Description |
---|---|
List<Strategy> |
TrainEA.getStrategies() |
Modifier and Type | Method and Description |
---|---|
void |
TrainEA.addStrategy(Strategy strategy)
Training strategies can be added to improve the training results.
|
Modifier and Type | Method and Description |
---|---|
List<Strategy> |
BaseBaumWelch.getStrategies() |
Modifier and Type | Method and Description |
---|---|
void |
BaseBaumWelch.addStrategy(Strategy strategy) |
Modifier and Type | Method and Description |
---|---|
List<Strategy> |
TrainKMeans.getStrategies() |
Modifier and Type | Method and Description |
---|---|
void |
TrainKMeans.addStrategy(Strategy strategy) |
Modifier and Type | Method and Description |
---|---|
List<Strategy> |
BasicTraining.getStrategies() |
List<Strategy> |
MLTrain.getStrategies() |
Modifier and Type | Method and Description |
---|---|
void |
BasicTraining.addStrategy(Strategy strategy)
Training strategies can be added to improve the training results.
|
void |
MLTrain.addStrategy(Strategy strategy)
Training strategies can be added to improve the training results.
|
Modifier and Type | Class and Description |
---|---|
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 |
StopTrainingStrategy
This strategy will indicate once training is no longer improving the neural
network by a specified amount, over a specified number of cycles.
|
Modifier and Type | Interface and Description |
---|---|
interface |
EndTrainingStrategy |
Modifier and Type | Class and Description |
---|---|
class |
EarlyStoppingStrategy
Stop early when validation set no longer improves.
|
class |
EndIterationsStrategy |
class |
EndMaxErrorStrategy |
class |
EndMinutesStrategy |
class |
SimpleEarlyStoppingStrategy
A simple early stopping strategy that halts training when the validation set no longer improves.
|
Modifier and Type | Method and Description |
---|---|
List<Strategy> |
TrainingJob.getStrategies() |
Modifier and Type | Class and Description |
---|---|
class |
RegularizationStrategy |
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.
|
Copyright © 2014. All Rights Reserved.