Package: hann 1.2
Emmanuel Paradis
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.
Authors:
hann_1.2.tar.gz
hann_1.2.tar.gz(r-4.7-arm64)hann_1.2.tar.gz(r-4.7-x86_64)hann_1.2.tar.gz(r-4.6-arm64)hann_1.2.tar.gz(r-4.6-x86_64)
hann_1.2.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
hann/json (API)
NEWS
| # Install 'hann' in R: |
| install.packages('hann', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/emmanuelparadis/hann/issues
Last updated from:c42e082665. Checks:6 OK. Indexed: no.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel-arm64 | OK | 143 | ||
| linux-devel-x86_64 | OK | 105 | ||
| source / vignettes | OK | 145 | ||
| linux-release-arm64 | OK | 116 | ||
| linux-release-x86_64 | OK | 103 | ||
| wasm-release | OK | 80 |
Exports:binarizebuildSigmacombinecontrol.hannhannhann1hann3tune.hann
Dependencies:
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Hopfield Artificial Neural Networks | hann-package |
| Helper Function to Prepare Data From Images | binarize |
| Hopfield Network Energy | buildSigma |
| Combine Several Neural Nets for Prediction | combine |
| Parameters for Neural Network Optimization | control.hann |
| Method Top-Level Functions | coef.hann fitted.hann hann labels.hann plot.hann predict.hann print.hann str.hann summary.hann |
| One-layer Hopfield ANN | hann1 print.hann1 |
| Three-layer Hopfield ANN | hann3 print.hann3 |
| Prediction | predict.hann1 predict.hann3 |
| Tune Hyperparameters | tune.hann |
