nn2poly
Neural Network Weights Transformation into Polynomial Coefficients
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.
- Version0.1.2
- R versionunknown
- LicenseMIT
- LicenseLICENSE
- Needs compilation?Yes
- nn2poly citation info
- Last release11/11/2024
Documentation
Team
Pablo Morala
Iñaki Ucar
Jose Ignacio Diez
Show author detailsRolesctr
Insights
Last 30 days
This package has been downloaded 509 times in the last 30 days. More downloads than an obscure whitepaper, but not enough to bring down any servers. A solid effort! The following heatmap shows the distribution of downloads per day. Yesterday, it was downloaded 23 times.
The following line graph shows the downloads per day. You can hover over the graph to see the exact number of downloads per day.
Last 365 days
This package has been downloaded 3,514 times in the last 365 days. Now we’re talking! This work is officially 'heard of in academic circles', just like those wild research papers on synthetic bananas. The day with the most downloads was Jan 20, 2025 with 56 downloads.
The following line graph shows the downloads per day. You can hover over the graph to see the exact number of downloads per day.
Data provided by CRAN
Binaries
Dependencies
- Imports4 packages
- Suggests12 packages
- Linking To2 packages