nnf_softplus

Applies element-wise, the function \(Softplus(x) = 1/\beta * log(1 + exp(\beta * x))\).

Provides functionality to define and train neural networks similar to
'PyTorch' by Paszke et al (2019) <arXiv:1912.01703> but written entirely in R
using the 'libtorch' library. Also supports low-level tensor operations and
'GPU' acceleration.

Daniel Falbel

torch

Tensors and Neural Networks with 'GPU' Acceleration

Javier Luraschi

Dmitriy Selivanov

Athos Damiani

Christophe Regouby

Krzysztof Joachimiak

Hamada S. Badr

 RStudio

nnf_softplus function

<dl><dt>input</dt>
<dd>(N,*) tensor, where * means, any number of additional
dimensions</dd>
<dt>beta</dt>
<dd>the beta value for the Softplus formulation. Default: 1</dd>
<dt>threshold</dt>
<dd>values above this revert to a linear function. Default: 20</dd></dl>

Arguments

Softplus — nnf_softplus

<dl>

<dt>input</dt>
<dd>(N,*) tensor, where * means, any number of additional
dimensions</dd>


<dt>beta</dt>
<dd>the beta value for the Softplus formulation. Default: 1</dd>


<dt>threshold</dt>
<dd>values above this revert to a linear function. Default: 20</dd>

</dl>

nnf_softplus: Softplus

Description

Usage

Arguments

Details