Trainable and explainable simplicial map neural networks

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-dimensiona...

ver descrição completa

Detalhes bibliográficos
Autores: Paluzo Hidalgo, Eduardo, González Díaz, Rocío, Gutiérrez Naranjo, Miguel Ángel
Formato: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2024
País:España
Recursos:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/156985
Acesso em linha:https://hdl.handle.net/11441/156985
https://doi.org/10.1016/j.ins.2024.120474
Access Level:acceso abierto
Palavra-chave:Explainable artificial intelligence
Simplicial maps
Training neural network
Descrição
Resumo: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 effective implementation are also newly introduced in this paper.