hann

MaRDI QIDQ7381148CRANFDO

Authors Emmanuel Paradis

Last update 26 January 2026

Copyright license GNU General Public License, version 3.0

Software version identifier PACKAGES.rds, 1.0, 1.1, 1.2

Description

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.

Cites work

• Neural networks and physical systems with emergent collective computational abilities

This page was built for software: hann