Package io.github.kirstenali.deepj.tensor

Class CpuNdAdamW

java.lang.Object

io.github.kirstenali.deepj.tensor.CpuNdAdamW

public final class CpuNdAdamW
extends Object

Logical-layout Adam arithmetic matches the original contiguous FLOAT32 update order.

Method Summary

Modifier and Type	Method	Description
static void	update(Tensor weight, Tensor gradient, Tensor first, Tensor second, float learningRate, float beta1, float beta2, float epsilon, float decay, float bc1, float bc2)

Methods inherited from class java.lang.Object

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

Method Details

update

public static void update(Tensor weight,
 Tensor gradient,
 Tensor first,
 Tensor second,
 float learningRate,
 float beta1,
 float beta2,
 float epsilon,
 float decay,
 float bc1,
 float bc2)