Crandore Hub

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.

Versions across snapshots

VersionRepositoryFileSize
1.2 rolling source/ R- hann_1.2.tar.gz 105.7 KiB
1.2 rolling linux/jammy R-4.5 hann_1.2.tar.gz 152.5 KiB
1.2 rolling linux/noble R-4.5 hann_1.2.tar.gz 152.6 KiB
1.2 latest source/ R- hann_1.2.tar.gz 105.7 KiB
1.2 latest linux/jammy R-4.5 hann_1.2.tar.gz 152.5 KiB
1.2 latest linux/noble R-4.5 hann_1.2.tar.gz 152.6 KiB
1.2 2026-04-23 source/ R- hann_1.2.tar.gz 105.7 KiB
1.2 2026-04-09 windows/windows R-4.5 hann_1.2.zip 276.4 KiB

Dependencies (latest)

Imports

Suggests