org.encog.neural.networks.training.strategy
Modifier and Type | Field and Description |
---|---|
static double |
MAX_MOMENTUM
The maximum value that momentum can go to.
|
static double |
MIN_IMPROVEMENT
The minimum improvement to adjust momentum.
|
static double |
MOMENTUM_CYCLES
How many cycles to accept before adjusting momentum.
|
static double |
MOMENTUM_INCREASE
How much to increase momentum by.
|
static double |
START_MOMENTUM
The starting momentum.
|
Constructor and Description |
---|
SmartMomentum() |
Modifier and Type | Method and Description |
---|---|
void |
init(MLTrain train)
Initialize this strategy.
|
void |
postIteration()
Called just after a training iteration.
|
void |
preIteration()
Called just before a training iteration.
|
public static final double MIN_IMPROVEMENT
public static final double MAX_MOMENTUM
public static final double START_MOMENTUM
public static final double MOMENTUM_INCREASE
public static final double MOMENTUM_CYCLES
public void init(MLTrain train)
public void postIteration()
postIteration
in interface Strategy
public void preIteration()
preIteration
in interface Strategy
Copyright © 2014. All Rights Reserved.