|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectorg.encog.ml.train.strategy.RequiredImprovementStrategy
public 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.
Constructor Summary | |
---|---|
RequiredImprovementStrategy(double required,
double threshold,
int cycles)
Construct a reset strategy. |
|
RequiredImprovementStrategy(double required,
int cycles)
Construct a reset strategy. |
|
RequiredImprovementStrategy(int cycles)
Reset if there is not at least a 1% improvement for 5 cycles. |
Method Summary | |
---|---|
void |
init(MLTrain train)
Initialize this strategy. |
void |
postIteration()
Called just after a training iteration. |
void |
preIteration()
Called just before a training iteration. |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Constructor Detail |
---|
public RequiredImprovementStrategy(double required, int cycles)
required
- The required error rate.cycles
- The number of cycles to reach that rate.public RequiredImprovementStrategy(double required, double threshold, int cycles)
required
- The required error rate.threshold
- The accepted threshold, don't reset if error is below this.cycles
- The number of cycles to reach that rate.public RequiredImprovementStrategy(int cycles)
cycles
- Method Detail |
---|
public void init(MLTrain train)
init
in interface Strategy
train
- The training algorithm.public void postIteration()
postIteration
in interface Strategy
public void preIteration()
preIteration
in interface Strategy
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |