org.ea.javacnn.trainers

Class AdamTrainer

java.lang.Object

org.ea.javacnn.trainers.Trainer

org.ea.javacnn.trainers.AdamTrainer

public class AdamTrainer
extends Trainer

Adaptive Moment Estimation is an update to RMSProp optimizer. In this running average of both the gradients and their magnitudes are used.

Constructor Summary

Constructors

Constructor and Description
AdamTrainer(JavaCNN net, int batch_size, float l2_decay)

Method Summary

Modifier and Type	Method and Description
void	initTrainData(BackPropResult bpr)
void	update(int i, int j, double gij, double[] p)

Methods inherited from class org.ea.javacnn.trainers.Trainer

train

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

AdamTrainer

public AdamTrainer(JavaCNN net,
                   int batch_size,
                   float l2_decay)

Method Detail

initTrainData

public void initTrainData(BackPropResult bpr)

Overrides:

initTrainData in class Trainer

update

public void update(int i,
                   int j,
                   double gij,
                   double[] p)

Specified by:

update in class Trainer