# -------------------------------------------- # CITATION file created with {cffr} R package # See also: https://docs.ropensci.org/cffr/ # -------------------------------------------- cff-version: 1.2.0 message: 'To cite package "nn2poly" in publications use:' type: software license: MIT title: 'nn2poly: Neural Network Weights Transformation into Polynomial Coefficients' version: 0.1.1 doi: 10.1016/j.neunet.2021.04.036 identifiers: - type: doi value: 10.32614/CRAN.package.nn2poly abstract: 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 . authors: - family-names: Morala given-names: Pablo email: moralapablo@gmail.com orcid: https://orcid.org/0000-0002-4109-2330 - family-names: Ucar given-names: IƱaki email: iucar@fedoraproject.org orcid: https://orcid.org/0000-0001-6403-5550 preferred-citation: type: article title: Towards a mathematical framework to inform neural network modelling via polynomial regression authors: - family-names: Morala given-names: Pablo email: moralapablo@gmail.com orcid: https://orcid.org/0000-0002-4109-2330 - family-names: Cifuentes given-names: J. Alexandra - family-names: Lillo given-names: Rosa E. - family-names: Ucar given-names: I\~naki journal: Neural Networks month: '10' year: '2021' volume: '142' doi: 10.1016/j.neunet.2021.04.036 start: '57' end: '72' repository: https://CRAN.R-project.org/package=nn2poly url: https://ibidat.github.io/nn2poly/ date-released: '2024-01-30' contact: - family-names: Morala given-names: Pablo email: moralapablo@gmail.com orcid: https://orcid.org/0000-0002-4109-2330 references: - type: article title: 'NNN2Poly: A Polynomial Representation for Deep Feed-Forward Artificial Neural Networks' authors: - family-names: Morala given-names: Pablo - family-names: Cifuentes given-names: J. Alexandra - family-names: Lillo given-names: Rosa E. - family-names: Ucar given-names: I\~naki journal: IEEE Transactions on Neural Networks and Learning Systems year: '2023' doi: 10.1109/TNNLS.2023.3330328