nn2poly: Neural Network Weights Transformation into Polynomial Coefficients (original) (raw)
Implements a method that builds the coefficients of a polynomial model that performs almost equivalently as a given neural network (densely connected). This is achieved using Taylor expansion at the activation functions. The obtained polynomial coefficients can be used to explain features (and their interactions) importance in the neural network, therefore working as a tool for interpretability or eXplainable Artificial Intelligence (XAI). See Morala et al. 2021 <doi:10.1016/j.neunet.2021.04.036>, and 2023 <doi:10.1109/TNNLS.2023.3330328>.
Version: | 0.1.2 |
---|---|
Depends: | R (≥ 3.5.0) |
Imports: | Rcpp, generics, matrixStats, pracma |
LinkingTo: | Rcpp, RcppArmadillo |
Suggests: | keras, tensorflow, reticulate, luz, torch, cowplot, ggplot2, patchwork, testthat (≥ 3.0.0), vdiffr, knitr, rmarkdown |
Published: | 2024-11-11 |
DOI: | 10.32614/CRAN.package.nn2poly |
Author: | Pablo Morala [aut, cre], Iñaki Ucar [aut], Jose Ignacio Diez [ctr] |
Maintainer: | Pablo Morala |
License: | MIT + file |
URL: | https://ibidat.github.io/nn2poly/ |
NeedsCompilation: | yes |
Citation: | nn2poly citation info |
Materials: | README NEWS |
CRAN checks: | nn2poly results |
Documentation:
Downloads:
Linking:
Please use the canonical formhttps://CRAN.R-project.org/package=nn2polyto link to this page.