nn2poly

CRANnn2polyMaRDI QIDQ5977296FDOQ5977296

Neural Network Weights Transformation into Polynomial Coefficients

Iñaki Ucar, Pablo Morala

Last update: 30 January 2024

Copyright license: MIT license, File License

Software version identifier: 0.1.0, 0.1.1

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 <doi:10.1016/j.neunet.2021.04.036>, and 2023 <doi:10.1109/TNNLS.2023.3330328>.

Cites work

• Towards a mathematical framework to inform neural network modelling via polynomial regression
• NN2Poly: A Polynomial Representation for Deep Feed-Forward Artificial Neural Networks

This page was built for software: nn2poly