Much like Adam is essentially RMSprop with momentum, Nadam is Adam RMSprop with Nesterov momentum.
optimizer_nadam(
lr = 0.002,
beta_1 = 0.9,
beta_2 = 0.999,
epsilon = NULL,
schedule_decay = 0.004,
clipnorm = NULL,
clipvalue = NULL
)float >= 0. Learning rate.
The exponential decay rate for the 1st moment estimates. float, 0 < beta < 1. Generally close to 1.
The exponential decay rate for the 2nd moment estimates. float, 0 < beta < 1. Generally close to 1.
float >= 0. Fuzz factor. If NULL, defaults to k_epsilon().
Schedule deacy.
Gradients will be clipped when their L2 norm exceeds this value.
Gradients will be clipped when their absolute value exceeds this value.
Default parameters follow those provided in the paper. It is recommended to leave the parameters of this optimizer at their default values.
On the importance of initialization and momentum in deep learning.
Other optimizers:
optimizer_adadelta(),
optimizer_adagrad(),
optimizer_adamax(),
optimizer_adam(),
optimizer_rmsprop(),
optimizer_sgd()