hann
1.2Hopfield Artificial Neural Networks
Overview
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.
Install
Health
- OK2026-08-0513 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
- NOTE2026-08-0112 OK · 1 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
- OK2026-03-1014 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
Documentation
- Examples that run
- 83%
- Documented parameters
- 86%
- Return-value docs
- 100%
- References docs
- 40%
Downloads
Repository
Repository practices
Checks run against github.com/emmanuelparadis/hann on 2026-08-16.
No development-tooling practices detected in the upstream repository.
Dependencies
Nothing depends on this yet.
Code & Tests
People & History
3 releases. Pick two to compare their code metrics. R releases are shown for context.
- RR 4.6.0 released · 2026-04-24
- 1.2Latest
- 1.12025-08-20 · diff ↗
- 1.02025-07-25
- RR 4.5.0 released · 2025-04-11
Package metadata
- First published
- 2025-07-25
- Total releases
- 3 / 1 yrs
- License
- GPL-3 OSI
- Download size
- 105 KB
- Installed size
- not tracked yet
- With dependencies
- not tracked yet
Cite
Cite this package
Run in R for the authors' preferred citation:
citation("hann")This is what citation() produces when a package has no citation file of its own. If it prints something else, use that.
Cite the R Observatory
For a number measured here: a download total, a coverage figure, an archival date.
From data release v2026-08-18, which the citation names so these numbers can be found later. More on citing and the projects behind them.