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.
| Version: | 1.1 |
| Published: | 2025-08-20 |
| Author: | Emmanuel Paradis 
[aut, cre, cph] |
| Maintainer: | Emmanuel Paradis <Emmanuel.Paradis at ird.fr> |
| BugReports: | https://github.com/emmanuelparadis/hann/issues |
| License: | GPL-3 |
| URL: | https://github.com/emmanuelparadis/hann |
| NeedsCompilation: | yes |
| CRAN checks: | hann results |
Documentation:
| Reference manual: | hann.html , hann.pdf |
| Vignettes: |
Introduction to Hopfield Networks (source, R code) |
Downloads:
| Package source: | hann_1.1.tar.gz |
| Windows binaries: | r-devel: hann_1.1.zip, r-release: hann_1.1.zip, r-oldrel: hann_1.1.zip |
| macOS binaries: | r-release (arm64): hann_1.1.tgz, r-oldrel (arm64): hann_1.1.tgz, r-release (x86_64): hann_1.1.tgz, r-oldrel (x86_64): hann_1.1.tgz |
| Old sources: | hann archive |
Linking:
Please use the canonical form https://CRAN.R-project.org/package=hann to link to this page.