Artículo
Trainable and explainable simplicial map neural networks
Autor/es | Paluzo Hidalgo, Eduardo
González Díaz, Rocío ![]() ![]() ![]() ![]() ![]() ![]() ![]() Gutiérrez Naranjo, Miguel Ángel ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Departamento | Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial Universidad de Sevilla. Departamento de Matemática Aplicada I (ETSII) |
Fecha de publicación | 2024 |
Fecha de depósito | 2024-04-23 |
Publicado en |
|
Resumen | 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, ... 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. |
Cita | Paluzo Hidalgo, E., González Díaz, R. y Gutiérrez Naranjo, M.Á. (2024). Trainable and explainable simplicial map neural networks. INFORMATION SCIENCES, 667, 120474. https://doi.org/10.1016/j.ins.2024.120474. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
15_Trainable_1-s2.0-S002002552 ... | 1.647Mb | ![]() | Ver/ | |