In this paper we present ExSpliNet, an interpretable and expressive neural network model. The model combines ideas of Kolmogorov neural networks, ensembles of probabilistic trees, and multivariate B-spline representations. We give a probabilistic interpretation of the model and show its universal approximation properties. We also discuss how it can be efficiently encoded by exploiting B-spline properties. Finally, we test the effectiveness of the proposed model on synthetic approximation problems and classical machine learning benchmark datasets.
@article{arxiv.2205.01510,
title = {ExSpliNet: An interpretable and expressive spline-based neural network},
author = {Daniele Fakhoury and Emanuele Fakhoury and Hendrik Speleers},
journal= {arXiv preprint arXiv:2205.01510},
year = {2022}
}