deepnetts.net.train.opt

Class AdaGradOptimizer

java.lang.Object

deepnetts.net.train.opt.AdaGradOptimizer

All Implemented Interfaces:

Optimizer, Serializable

public final class AdaGradOptimizer
extends Object
implements Optimizer, Serializable

Implementation of ADAGRAD Optimizer , which uses sum of squared previous gradients to adjust a global learning rate for each weight.

Author:

Zoran Sevarac

See Also:

Serialized Form

Field Summary

Fields inherited from interface deepnetts.net.train.opt.Optimizer

COL_IDX, DEPTH_IDX, EPS, FOURTH_DIM_IDX, ROW_IDX

Constructor Summary

Constructors

Constructor and Description
AdaGradOptimizer(AbstractLayer layer)

Method Summary

Modifier and Type	Method and Description
float	calculateDeltaBias(float grad, int idx)
float	calculateDeltaWeight(float grad, int... idxs)
void	setLearningRate(float learningRate)

Methods inherited from class java.lang.Object

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

Methods inherited from interface deepnetts.net.train.opt.Optimizer

create

Constructor Detail

AdaGradOptimizer

public AdaGradOptimizer(AbstractLayer layer)

Method Detail

calculateDeltaWeight

public float calculateDeltaWeight(float grad,
                                  int... idxs)

Specified by:

calculateDeltaWeight in interface Optimizer

calculateDeltaBias

public float calculateDeltaBias(float grad,
                                int idx)

Specified by:

calculateDeltaBias in interface Optimizer

setLearningRate

public void setLearningRate(float learningRate)

Specified by:

setLearningRate in interface Optimizer