Package: nn2poly Title: Neural Network Weights Transformation into Polynomial Coefficients Version: 1.0.1 Authors@R: c( person(given = "Pablo", family = "Morala", role = c("aut", "cre"), email = "moralapablo@gmail.com", comment = c(ORCID = "0000-0002-4109-2330")), person(given = "Iñaki", family = "Ucar", role = c("aut"), email = "iucar@fedoraproject.org", comment = c(ORCID = "0000-0001-6403-5550")), person(given = "Jose Ignacio", family = "Diez", role = c("ctr")) ) Description: 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 , and 2023 . License: MIT + file LICENSE Encoding: UTF-8 Depends: R (>= 3.5.0) Imports: Rcpp, generics Suggests: keras, tensorflow, reticulate, luz, torch, cowplot, ggplot2, patchwork, testthat (>= 3.0.0), vdiffr, knitr, rmarkdown LinkingTo: Rcpp, RcppArmadillo VignetteBuilder: knitr Config/roxygen2/version: 8.0.0 Config/testthat/edition: 3 URL: https://ibidat.github.io/nn2poly/, https://github.com/IBiDat/nn2poly BugReports: https://github.com/IBiDat/nn2poly/issues NeedsCompilation: yes Packaged: 2026-10-26 09:02:24 UTC; root Author: Pablo Morala [aut, cre] (ORCID: ), Iñaki Ucar [aut] (ORCID: ), Jose Ignacio Diez [ctr] Maintainer: Pablo Morala Repository: https://cran.r-universe.dev Date/Publication: 2026-07-17 22:40:02 UTC RemoteUrl: https://github.com/cran/nn2poly RemoteRef: HEAD RemoteSha: ce52ffba0ec48d9c0cb22d58d4c2519694e40b7c