Skip to content

nn2poly

1.0.1

Neural Network Weights Transformation into Polynomial Coefficients

0packages depend
4.5Kdownloads / year
45.0%test coverage
13/13checks pass

Overview

About
Maintained by Pablo MoralaFirst published 2024-01-246 releasesCRAN page ↗GitHub ↗

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.

Install

Health

CRAN checks
13OK
Slowest check: 4.3 min · r-devel-windows-x86_64
Code health
Yes
Tests · ratio 1.70
45.0%
Coverage · measured lines
100%
Documentation · exports
2
Dependencies · direct
Check history
  • OK2026-08-05
    13 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
  • NOTE2026-08-01
    12 OK · 1 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
  • OK2026-04-22
    14 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
  • ERROR2026-04-18
    13 OK · 0 NOTE · 0 WARNING · 1 ERROR · 0 FAILURE
  • OK2026-03-10
    14 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE

Documentation

Documentation
READMEYes · 188 wordsVignettesYes · dynamicpkgdown siteNoNEWSYes · 100% structuredCode of conductNoContributing guideNo
Examples that run
60%
Documented parameters
100%
Return-value docs
75%
References docs
0%

Downloads

4.5K
CRAN downloads in the past year
Rank #11,065 · ~12/day · ~377/mo
Daily download trend is not available in this view yet.
25130 days
87990 days
4.5K1 year
Compare downloads with other packages →
Also on416 r2u20 autocran

Repository

Repository
12Stars
1Forks
5Open issues
0Open PRs
5Releases
151Commits
4Contributors
151 commits · Last activity 2026-08-20 · +9.1% stars, 30d

Stars over time

2025-03-05 · 92026-08-02 · 12

Repository practices

Upstream repositoryBeta

4 development-tooling and community-health practices detected across 4 families in the upstream repository

Checks run against github.com/ibidat/nn2poly on 2026-08-16.

Continuous integration (1)
GitHub Actions
CRAN release process (1)
cran-comments.md
Automation and maintenance (1)
Dependabot
Lint, format, editor (1)
RStudio project
How this is detected·Detection ruleset v1 (2026-07-18)

Dependencies

Declared dependencies
16 external dependencies (excludes base and recommended)
Depends (1)
R >= 3.5.0
Imports (2)
LinkingTo (2)
Enhances (0)
none
Reverse dependencies
0direct
0indirect

Nothing depends on this yet.

Code & Tests

People & History

People (3)
Maintainer (1)
Author, Maintainer
Authors (2)
Author, Maintainer
Other (1)
Package Timeline

6 releases. Pick two to compare their code metrics. R releases are shown for context.

  • 1.0.1Latest
    2026-07-18 · current release · diff ↗
  • 1.0.0
    2026-07-17 · diff ↗
  • R
    R 4.6.0 released · 2026-04-24
  • 0.1.3
    2025-12-12 · diff ↗
  • R
    R 4.5.0 released · 2025-04-11
  • 0.1.2
    2024-11-11 · diff ↗
  • R
    R 4.4.0 released · 2024-04-24
  • 0.1.1
    2024-01-30 · diff ↗
  • 0.1.0
    2024-01-24
  • R
    R 4.3.0 released · 2023-04-21

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
Installed size
not tracked yet
With dependencies
not tracked yet

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("nn2poly")
Morala, P., Diez, J. I., & Ucar, I. (2026). nn2poly: Neural Network Weights Transformation into Polynomial Coefficients (Version 1.0.1) [Computer software]. https://doi.org/10.32614/CRAN.package.nn2poly

This is what citation() produces when a package has no citation file of its own. If it prints something else, use that.

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 v2026-08-22. https://doi.org/10.5281/zenodo.21843040

From data release v2026-08-22, 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