Neural Network Weights Transformation into Polynomial Coefficients
Add constraints to a neural network
Polynomial evaluation
Build a luz model composed of a linear stack of layers
Obtain polynomial representation
Plots a comparison between two sets of points.
Plots activation potentials and Taylor expansion.
Plot method for nn2poly objects.
Predict method for nn2poly objects.
Objects exported from other packages
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>.
Useful links