|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectorg.encog.ml.train.strategy.ResetStrategy
public 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. This can be useful to throw out initially "bad/hard" random initializations of the weight matrix.
Constructor Summary | |
---|---|
ResetStrategy(double required,
int cycles)
Construct a reset strategy. |
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 ResetStrategy(double required, int cycles)
required
- The required error rate.cycles
- The number of cycles to reach that rate.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 |