hann-package

hann provides tools to build Hopfield-based artificial neural
 networks. Two types of networks can be built: one-layer Hopfield
 network, and three-layer network with a hidden (convoluted) layer.
The complete list of functions can be displayed with
 <code><a href="/link/library(help%20%3D%20hann)?package=hann&version=1.2" data-mini-rdoc="hann::library(help = hann)">library(help = hann)</a></code>. See the vignette
 ``IntroductionHopfieldNetworks'' for several examples.
More information on hann can be found at
 <a href="https://github.com/emmanuelparadis/hann">https://github.com/emmanuelparadis/hann</a>.

package

Builds and optimizes Hopfield artificial neural networks (Hopfield, 1982, <doi:10.1073/pnas.79.8.2554>). One-layer and three-layer models are implemented. The energy of the Hopfield network is minimized with formula from Krotov and Hopfield (2016, <doi:10.48550/ARXIV.1606.01164>). Optimization (supervised learning) is done through a gradient-based method. Classification is done with S3 methods predict(). Parallelization with 'OpenMP' is used if available during compilation.

Emmanuel Paradis

hann

Hopfield Artificial Neural Networks

hann-package function

Emmanuel Paradis
Maintainer: Emmanuel Paradis &lt;Emmanuel.Paradis@ird.fr&gt;

Author

hann provides tools to build Hopfield-based artificial neural
 networks. Two types of networks can be built: one-layer Hopfield
 network, and three-layer network with a hidden (convoluted) layer.
The complete list of functions can be displayed with
 <code><a href='https://rdrr.io/r/base/library.html'>library(help = hann)</a></code>. See the vignette
 ``IntroductionHopfieldNetworks'' for several examples.
More information on hann can be found at
 <a href='https://github.com/emmanuelparadis/hann'>https://github.com/emmanuelparadis/hann</a>.

hann-package: Hopfield Artificial Neural Networks

Description

Arguments

Author