Publicación:
Achieving faithful explainability in feedforward neural networks through accurately computed feature attribution

Vista sencilla de ítem
dc.contributor.authorCarles-Bou, Jose L.
dc.contributor.authorCarmona Suárez, Enrique J.
dc.contributor.funderAgencia Estatal de Investigación. España
dc.date.accessioned2025-11-24T17:20:44Z
dc.date.available2025-11-24T17:20:44Z
dc.date.issued2025-11-14
dc.descriptionThe registered version of this article, first published in Neural Networks, is available online at the publisher's website: Elsevier, https://doi.org/10.1016/j.neunet.2025.108277
dc.descriptionLa versión registrada de este artículo, publicado por primera vez en Neural Networks, está disponible en línea en el sitio web del editor: Elsevier, https://doi.org/10.1016/j.neunet.2025.108277
dc.description.abstractThe rapid advancements in machine learning have led to the deployment of complex models in critical domains such as healthcare, finance, and autonomous systems. Despite their remarkable predictive performance, the opaque nature of these models presents significant challenges for interpretability, which is essential for trust, accountability, and regulatory compliance. Explainable Artificial Intelligence (XAI) has emerged as a crucial field addressing these challenges by making black-box models more transparent. In this paper, we propose a novel model-specific local post-hoc explanation method for feedforward neural networks (FNNs) built on a solid mathematical foundation. Our approach enables the exact computation of input feature attributions for individual predictions and achieves perfect fidelity in replicating model behavior. These two properties, combined with competitive computational efficiency, demonstrate the superior performance of the proposed method compared to state-of-the-art XAI techniques. We validate the method through extensive experiments, showing its versatility across diverse types of problems. This work enhances interpretability and trust in AI systems by providing a reliable explanation framework applicable across a wide range of scenarios modeled with FNNs.en
dc.description.provenanceMade available in DSpace on 2025-11-24T17:20:44Z (GMT). No. of bitstreams: 1 Achieving faithful explainability in feedforward neural networks.pdf: 3207250 bytes, checksum: e89412acda5c148571f2cdc109460a30 (MD5) Previous issue date: 2025-11-14en
dc.description.sponsorshipThis work was supported by the Ministerio de Ciencia, Innovación y Universidades, Government of Spain, through the PID2023-148913OB-I00.
dc.description.versionversión publicada
dc.identifier.citationCarles-Bou, J. L., & Carmona, E. J. (2026). Achieving faithful explainability in feedforward neural networks through accurately computed feature attribution. Neural Networks, 195. https://doi.org/10.1016/J.NEUNET.2025.108277
dc.identifier.doihttps://doi.org/10.1016/j.neunet.2025.108277
dc.identifier.issn1879-2782
dc.identifier.urihttps://hdl.handle.net/20.500.14468/30912
dc.journal.titleNeural Networks
dc.journal.volume195
dc.language.isoen
dc.publisherElsevier
dc.relation.centerE.T.S. de Ingeniería Informática
dc.relation.projectidinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2023-148913OB-I00
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/deed.es
dc.subject1203.04 Inteligencia artificial
dc.subject.keywordsExplainable AIen
dc.subject.keywordsFeature attributionen
dc.subject.keywordsFaithful explainabilityen
dc.subject.keywordsPost-hoc explanationen
dc.subject.keywordsLocal explanationen
dc.subject.keywordsFeedforward neural networksen
dc.titleAchieving faithful explainability in feedforward neural networks through accurately computed feature attributionen
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublication5e870768-cc8e-47fe-9662-25cd1385fd3c
relation.isAuthorOfPublication.latestForDiscovery5e870768-cc8e-47fe-9662-25cd1385fd3c
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Achieving faithful explainability in feedforward neural networks.pdf
Tamaño:
3.06 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.62 KB
Formato:
Item-specific license agreed to upon submission
Descripción:
Descargar
Colecciones
Artículos y papers