dc.creator | Jiménez Navarro, Manuel Jesús | es |
dc.creator | Martínez Ballesteros, María del Mar | es |
dc.creator | Martínez Álvarez, Francisco | es |
dc.creator | Asencio Cortés, Gualberto | es |
dc.date.accessioned | 2024-04-12T09:49:30Z | |
dc.date.available | 2024-04-12T09:49:30Z | |
dc.date.issued | 2023-08 | |
dc.identifier.citation | Jiménez Navarro, M.J., Martínez Ballesteros, M.d.M., Martínez Álvarez, F. y Asencio Cortés, G. (2023). Explaining Learned Patterns in Deep Learning by Association Rules Mining. En 18th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2023) (132-141), Salamanca (España): SpringerLink. | |
dc.identifier.isbn | 978-3-031-42535-6 | es |
dc.identifier.isbn | 978-3-031-42536-3 (online) | es |
dc.identifier.uri | https://hdl.handle.net/11441/156832 | |
dc.description.abstract | This paper proposes a novel approach that combines an association rule algorithm with a deep learning model to enhance the interpretability of prediction outcomes. The study aims to gain insights into the patterns that were learned correctly or incorrectly by the model. To identify these scenarios, an association rule algorithm is applied to extract the patterns learned by the deep learning model. The rules are then analyzed and classified based on specific metrics to draw conclusions about the behavior of the model. We applied this approach to a well-known dataset in various scenarios, such as underfitting and overfitting. The results demonstrate that the combination of the two techniques is highly effective in identifying the patterns learned by the model and analyzing its performance in different scenarios, through error analysis. We suggest that this methodology can enhance the transparency and interpretability of black-box models, thus improving their reliability for real-world applications. | es |
dc.description.sponsorship | Ministerio de Ciencia e Innovación PID2020-117954RB | es |
dc.description.sponsorship | Ministerio de Ciencia e innovación TED2021-131311B | es |
dc.description.sponsorship | Junta de Andalucía PY20-00870 | es |
dc.description.sponsorship | Junta de Andalucía PYC20 RE 078 USE | es |
dc.description.sponsorship | Junta de Andalucía UPO-138516 | es |
dc.format | application/pdf | es |
dc.format.extent | 10 | es |
dc.language.iso | eng | es |
dc.publisher | SpringerLink | es |
dc.relation.ispartof | 18th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2023) (2023), pp. 132-141. | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Association rules | es |
dc.subject | Apriori | es |
dc.subject | Deep learning | es |
dc.subject | Interpretability | es |
dc.subject | Explainable AI | es |
dc.title | Explaining Learned Patterns in Deep Learning by Association Rules Mining | es |
dc.type | info:eu-repo/semantics/conferenceObject | es |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos | es |
dc.relation.projectID | PID2020-117954RB | es |
dc.relation.projectID | TED2021-131311B | es |
dc.relation.projectID | PY20-00870 | es |
dc.relation.projectID | PYC20 RE 078 USE | es |
dc.relation.projectID | UPO-138516 | es |
dc.relation.publisherversion | https://link.springer.com/chapter/10.1007/978-3-031-42536-3_13 | es |
dc.identifier.doi | 10.1007/978-3-031-42536-3_13 | es |
dc.publication.initialPage | 132 | es |
dc.publication.endPage | 141 | es |
dc.eventtitle | 18th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2023) | es |
dc.eventinstitution | Salamanca (España) | es |
dc.contributor.funder | Ministerio de Ciencia e Innovación (MICIN). España | es |
dc.contributor.funder | Junta de Andalucía | es |