Trainable and Explainable Simplicial Map Neural Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Paluzo-Hidalgo, Eduardo, Gutiérrez-Naranjo, Miguel A., Gonzalez-Diaz, Rocio
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911806075699200
author Paluzo-Hidalgo, Eduardo
Gutiérrez-Naranjo, Miguel A.
Gonzalez-Diaz, Rocio
author_facet Paluzo-Hidalgo, Eduardo
Gutiérrez-Naranjo, Miguel A.
Gonzalez-Diaz, Rocio
contents Simplicial map neural networks (SMNNs) are topology-based neural networks with interesting properties such as universal approximation ability and robustness to adversarial examples under appropriate conditions. However, SMNNs present some bottlenecks for their possible application in high-dimensional datasets. First, SMNNs have precomputed fixed weight and no SMNN training process has been defined so far, so they lack generalization ability. Second, SMNNs require the construction of a convex polytope surrounding the input dataset. In this paper, we overcome these issues by proposing an SMNN training procedure based on a support subset of the given dataset and replacing the construction of the convex polytope by a method based on projections to a hypersphere. In addition, the explainability capacity of SMNNs and an effective implementation are also newly introduced in this paper.
format Preprint
id arxiv_https___arxiv_org_abs_2306_00010
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Trainable and Explainable Simplicial Map Neural Networks
Paluzo-Hidalgo, Eduardo
Gutiérrez-Naranjo, Miguel A.
Gonzalez-Diaz, Rocio
Machine Learning
Artificial Intelligence
Algebraic Topology
Simplicial map neural networks (SMNNs) are topology-based neural networks with interesting properties such as universal approximation ability and robustness to adversarial examples under appropriate conditions. However, SMNNs present some bottlenecks for their possible application in high-dimensional datasets. First, SMNNs have precomputed fixed weight and no SMNN training process has been defined so far, so they lack generalization ability. Second, SMNNs require the construction of a convex polytope surrounding the input dataset. In this paper, we overcome these issues by proposing an SMNN training procedure based on a support subset of the given dataset and replacing the construction of the convex polytope by a method based on projections to a hypersphere. In addition, the explainability capacity of SMNNs and an effective implementation are also newly introduced in this paper.
title Trainable and Explainable Simplicial Map Neural Networks
topic Machine Learning
Artificial Intelligence
Algebraic Topology
url https://arxiv.org/abs/2306.00010