optimizer_adam: Adam optimizer

Description Usage Arguments References Note See Also

View source: R/optimizers.R

Description

Adam optimizer as described in Adam - A Method for Stochastic Optimization.

Usage

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
optimizer_adam(
  lr = 0.001,
  beta_1 = 0.9,
  beta_2 = 0.999,
  epsilon = NULL,
  decay = 0,
  amsgrad = FALSE,
  clipnorm = NULL,
  clipvalue = NULL
)

Arguments

lr

float >= 0. Learning rate.

beta_1

The exponential decay rate for the 1st moment estimates. float, 0 < beta < 1. Generally close to 1.

beta_2

The exponential decay rate for the 2nd moment estimates. float, 0 < beta < 1. Generally close to 1.

epsilon

float >= 0. Fuzz factor. If NULL, defaults to k_epsilon().

decay

float >= 0. Learning rate decay over each update.

amsgrad

Whether to apply the AMSGrad variant of this algorithm from the paper "On the Convergence of Adam and Beyond".

clipnorm

Gradients will be clipped when their L2 norm exceeds this value.

clipvalue

Gradients will be clipped when their absolute value exceeds this value.

References

Note

Default parameters follow those provided in the original paper.

See Also

Other optimizers: optimizer_adadelta(), optimizer_adagrad(), optimizer_adamax(), optimizer_nadam(), optimizer_rmsprop(), optimizer_sgd()


keras documentation built on March 30, 2021, 1:06 a.m.