Package: nn2poly 0.1.1

Pablo Morala

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>.

Authors:Pablo Morala [aut, cre], Iñaki Ucar [aut], Jose Ignacio Diez [ctr]

nn2poly_0.1.1.tar.gz
nn2poly_0.1.1.zip(r-4.5)nn2poly_0.1.1.zip(r-4.4)nn2poly_0.1.1.zip(r-4.3)
nn2poly_0.1.1.tgz(r-4.4-x86_64)nn2poly_0.1.1.tgz(r-4.4-arm64)nn2poly_0.1.1.tgz(r-4.3-x86_64)nn2poly_0.1.1.tgz(r-4.3-arm64)
nn2poly_0.1.1.tar.gz(r-4.5-noble)nn2poly_0.1.1.tar.gz(r-4.4-noble)
nn2poly_0.1.1.tgz(r-4.4-emscripten)nn2poly_0.1.1.tgz(r-4.3-emscripten)
nn2poly.pdf |nn2poly.html✨
nn2poly/json (API)
NEWS

Peer review:

Bug tracker:https://github.com/ibidat/nn2poly/issues

On CRAN:

4 exports 9 stars 1.91 score 5 dependencies 16 scripts 190 downloads

Last updated 8 months agofrom:1ab5dd3788. Checks:OK: 1 NOTE: 8. Indexed: yes.

Exports:add_constraintsfitluz_model_sequentialnn2poly

Dependencies:genericsmatrixStatspracmaRcppRcppArmadillo