Nothing
hann: Hopfield Artificial Neural Networks
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.
Getting started
Browse package contents
Package details |
|
|---|---|
| Author | Emmanuel Paradis [aut, cre, cph] (ORCID: <https://orcid.org/0000-0003-3092-2199>) |
| Maintainer | Emmanuel Paradis <Emmanuel.Paradis@ird.fr> |
| License | GPL-3 |
| Version | 1.0 |
| URL | https://github.com/emmanuelparadis/hann |
| Package repository | View on CRAN |
| Installation |
Install the latest version of this package by entering the following in R:
|
Try the hann package in your browser
Any scripts or data that you put into this service are public.
