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.

Tensors and Neural Networks with 'GPU' Acceleration

package-ubuntu-20.04-r-4.0.5#cran#torch-0.3.0

<p>Applies element-wise, the function <i>SoftSign(x) = x/(1 + |x|</i>
</p>

<table summary="R argblock"><tr valign="top">
<td><code>input</code></td>
<td>
<p>(N,*) tensor, where * means, any number of additional
dimensions</p>
</td>
</tr></table>

package-ubuntu-20.04-r-4.0.5#cran#torch-0.3.0#docs#nnf_softsign

nnf_softsign

Description

Usage

Arguments

torch

We don't support your browser anymore