Skip to content

nn2poly

1.0.1Package record

Neural Network Weights Transformation into Polynomial Coefficients

0packages depend
4.1Kdownloads / year
45.0%test coverage
13/13flavors OK

Overview

About

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.

Changes in 1.0.1
  • Fix UB in hash implementation (#84).

From NEWS.md in the release

Install

Health

CRAN checks
13OK
Slowest check: 3.9 min · r-devel-windows-x86_64
Status changes
  • OK13 OK2026-08-05
  • NOTE12 OK, 1 NOTE2026-08-01
  • OK14 OK2026-04-22
  • ERROR13 OK, 1 ERROR2026-04-18
  • OK14 OK2026-03-10
Advisories

none known

Documentation

In release 1.0.1
READMEYes · 188 wordsVignettesYes · 3 · staticNEWSYes · 100% structured · mentions 1.0.1Citation fileYes · cites a publicationWebsiteYes · pkgdown
Help pages
9 (1 internal)
Examples that run
60%3 run in a plain check · 2 never run
Exported functions with examples
75%
Documented parameters
100%
Return-value docs
75%
Help pages citing references
0%

Downloads

4.1K
CRAN downloads in the past year
Rank #10,702 · ~11/day · ~341/mo
Daily download trend is not available in this view yet.
31330 days
96390 days
4.1K1 year
Compare downloads with other packages →
Also on391 r2u1 autocran

Repository

12Stars
1Forks
5Open issues
0Open PRs
5Releases
151Commits
4Commit identities
151 commits · Last activity 2026-07-23 · 0% stars, 30d · Default branch at 1.0.1.9000, ahead of CRAN 1.0.1 (checked 2026-10-18)
Responsiveness
How these are sampled
PRs merged (all time)
87%
Median days to close, 50 most recently updated closed issues
16
Median days to close, 50 most recently updated closed PRs
0

Stars over time

2025-03-05 · 92026-08-02 · 12
PracticesBeta

9 development-tooling and community-health practices detected across 6 families in the upstream repository

Checks run against github.com/ibidat/nn2poly on 2026-10-18.

Continuous integration (2)
GitHub ActionsR CMD check workflow

The R CMD check workflow runs on Linux, macOS and Windows, and on R-devel

Docs source (3)
pkgdown

GitHub Pages site last deployed 2026-07-18 · The repository has a site deploy workflow

pkgdown site last built 2026-07-18

Coverage (1)
Coverage reporting
CRAN release process (1)
cran-comments.md
Show all practicesHide 2 practices
Automation and maintenance (1)
Dependabot
Lint, format, editor (1)
RStudio project
How this is detected·Detection ruleset v3 (2026-09-26)

Dependencies

Declared dependencies
16 external dependencies (excludes base and recommended)

Installing nn2poly adds 3 packages (2 with compiled code, 2.8 MB of source tarballs). Heaviest: Rcpp 1.8 MB, RcppArmadillo 1.0 MB, generics 46 KB.

Depends (1)
R >= 3.5.0
Imports (2)
LinkingTo (2)
Enhances (0)
none
Reverse dependencies
0direct
0indirect

Nothing depends on this yet.

People & History

People (3)
Author, Maintainer since 0.1.0 (2024)
Releases (6)

Pick two releases to compare their code metrics.

Package metadata

First published
2024-01-24
Total releases
6 / 2 yrs
License
MIT + file LICENSE OSI
Minimum R
≥ 3.5.0
Download size
1.6 MB

Cite

Cite this package

Run in R for the authors' entry:

citation("nn2poly")

The package provides a citation file, so citation() returns the authors' own entry.

It points to 10.1016/j.neunet.2021.04.036, 10.1109/tnnls.2023.3330328.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

APA

Balamuta, J. J. (2026). R Observatory: Metrics for nn2poly version 1.0.1 [Data set]. HJJB, LLC. Data release v2026-10-20. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-20, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →

Privacy choices

These apply to this browser and are stored on this device only. Nothing about your choice is sent to us.

Read the privacy policy