adam {CNN} R Documentation

Adaptive Moment Estimation is an update to RMSProp optimizer. In this running average of both the

Description

gradients and their magnitudes are used.

Usage

adam(batch.size,
    l2.decay = 0.001,
    beta1 = 0.9,
    beta2 = 0.999);

Arguments

batch.size

[as integer]

l2.decay

[as double]

beta1

[as double]

beta2

[as double]

Details

Authors

MLkit

Value

this function returns data object of type TrainerAlgorithm.

clr value class

Examples

[Package CNN version 1.0.0.0 Index]