Other packages > Find by keyword >

nn2poly  

Neural Network Weights Transformation into Polynomial Coefficients
View on CRAN: Click here


Download and install nn2poly package within the R console
Install from CRAN:
install.packages("nn2poly")

Install from Github:
library("remotes")
install_github("cran/nn2poly")

Install by package version:
library("remotes")
install_version("nn2poly", "0.1.3")



Attach the package and use:
library("nn2poly")
Maintained by
Pablo Morala
[Scholar Profile | Author Map]
All associated links for this package
First Published: 2024-01-24
Latest Update: 2024-11-11
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 .
How to cite:
Pablo Morala (2024). nn2poly: Neural Network Weights Transformation into Polynomial Coefficients. R package version 0.1.3, https://cran.r-project.org/web/packages/nn2poly. Accessed 05 Mar. 2026.
Previous versions and publish date:
0.1.0 (2024-01-24 15:50), 0.1.1 (2024-01-30 10:10), 0.1.2 (2024-11-11 16:20)
Other packages that cited nn2poly R package
View nn2poly citation profile
Other R packages that nn2poly depends, imports, suggests or enhances
Complete documentation for nn2poly
Downloads during the last 30 days

Today's Hot Picks in Authors and Packages

nextGenShinyApps  
Craft Exceptional 'R Shiny' Applications and Dashboards with Novel Responsive Tools
Nove responsive tools for designing and developing 'Shiny' dashboards and applications. The scripts ...
Download / Learn more Package Citations See dependency  
diffIRT  
Diffusion IRT Models for Response and Response Time Data
Package to fit diffusion-based IRT models to response and response time data. Models are fit using ...
Download / Learn more Package Citations See dependency  
roccv  
ROC for Cross Validation Results
Cross validate large genetic data while specifying clinical variables that should always be in the m ...
Download / Learn more Package Citations See dependency  
imagefx  
Extract Features from Images
Synthesize images into characteristic features for time-series analysis or machine learning applicat ...
Download / Learn more Package Citations See dependency  
ClimClass  
Climate Classification According to Several Indices
Classification of climate according to Koeppen - Geiger, of aridity indices, of continentality indi ...
Download / Learn more Package Citations See dependency  
pinp  
'pinp' is not 'PNAS'
A 'PNAS'-alike style for 'rmarkdown', derived from the 'Proceedings of the National Academy of Scie ...
Download / Learn more Package Citations See dependency  

26,264

R Packages

223,360

Dependencies

70,244

Author Associations

26,265

Publication Badges

© Copyright since 2022. All right reserved, rpkg.net.  Based in Cambridge, Massachusetts, USA