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>.
Package details |
|
---|---|
Author | Pablo Morala [aut, cre] (<https://orcid.org/0000-0002-4109-2330>), Iñaki Ucar [aut] (<https://orcid.org/0000-0001-6403-5550>), Jose Ignacio Diez [ctr] |
Maintainer | Pablo Morala <moralapablo@gmail.com> |
License | MIT + file LICENSE |
Version | 0.1.1 |
URL | https://ibidat.github.io/nn2poly/ |
Package repository | View on CRAN |
Installation |
Install the latest version of this package by entering the following in R:
|
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.