org.deeplearning4j.optimize

Class GradientAdjustment

java.lang.Object

org.deeplearning4j.optimize.GradientAdjustment

public class GradientAdjustment
extends Object

Gradient adjustment

Author:

Adam Gibson

Method Summary

Modifier and Type	Method and Description
static void	updateGradientAccordingToParams(int iteration, int batchSize, NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray params, org.nd4j.linalg.api.ndarray.INDArray gradient, org.nd4j.linalg.learning.GradientUpdater adaGrad, org.nd4j.linalg.api.ndarray.INDArray lastStep, String paramType) Deprecated.

Methods inherited from class java.lang.Object

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

Method Detail

updateGradientAccordingToParams

@Deprecated
public static void updateGradientAccordingToParams(int iteration,
                                                               int batchSize,
                                                               NeuralNetConfiguration conf,
                                                               org.nd4j.linalg.api.ndarray.INDArray params,
                                                               org.nd4j.linalg.api.ndarray.INDArray gradient,
                                                               org.nd4j.linalg.learning.GradientUpdater adaGrad,
                                                               org.nd4j.linalg.api.ndarray.INDArray lastStep,
                                                               String paramType)

Deprecated.

Updates each variable wrt its gradient

Parameters:

iteration - the iteration

batchSize - the batch size of the input

conf - the configuration

params - the model params

gradient - the gradients for the variables

adaGrad - the adagrad map (per variable adagrad entries(