nn_selu: SELU module

In torch: Tensors and Neural Networks with 'GPU' Acceleration

SELU module

Description

Applied element-wise, as:

Usage

nn_selu(inplace = FALSE)

Arguments

inplace

(bool, optional): can optionally do the operation in-place. Default: FALSE

Details

\mbox{SELU}(x) = \mbox{scale} * (\max(0,x) + \min(0, \alpha * (\exp(x) - 1)))

with \alpha = 1.6732632423543772848170429916717 and \mbox{scale} = 1.0507009873554804934193349852946.

More details can be found in the paper Self-Normalizing Neural Networks.

Shape

• Input: (N, *) where * means, any number of additional dimensions

• Output: (N, *), same shape as the input

Examples

if (torch_is_installed()) {
m <- nn_selu()
input <- torch_randn(2)
output <- m(input)
}

torch documentation built on May 29, 2024, 9:54 a.m.