VCI-LSTM: Vector choquet integral-based long short-term memory
| dc.contributor.author | Ferrero Jaurrieta, Mikel | |
| dc.contributor.author | Takáč, Zdenko | |
| dc.contributor.author | Fernández Fernández, Francisco Javier | |
| dc.contributor.author | Horanská, Lubomíra | |
| dc.contributor.author | Pereira Dimuro, Graçaliz | |
| dc.contributor.author | Montes Rodríguez, Susana | |
| dc.contributor.author | Díaz, Irene | |
| dc.contributor.author | Bustince Sola, Humberto | |
| dc.contributor.department | Estadística, Informática y Matemáticas | es_ES |
| dc.contributor.department | Estatistika, Informatika eta Matematika | eu |
| dc.date.accessioned | 2023-05-10T18:26:37Z | |
| dc.date.available | 2023-05-10T18:26:37Z | |
| dc.date.issued | 2022 | |
| dc.date.updated | 2023-05-10T18:18:45Z | |
| dc.description.abstract | Choquet integral is a widely used aggregation operator on one-dimensional and interval-valued information, since it is able to take into account the possible interaction among data. However, there are many cases where the information taken into account is vectorial, such as Long Short-Term Memories (LSTM). LSTM units are a kind of Recurrent Neural Networks that have become one of the most powerful tools to deal with sequential information since they have the power of controlling the information flow. In this paper, we first generalize the standard Choquet integral to admit an input composed by <inline-formula><tex-math notation="LaTeX">$n$</tex-math></inline-formula>-dimensional vectors, which produces an <inline-formula><tex-math notation="LaTeX">$n$</tex-math></inline-formula>-dimensional vector output. We study several properties and construction methods of vector Choquet integrals. Then, we use this integral in the place of the summation operator, introducing in this way the new VCI-LSTM architecture. Finally, we use the proposed VCI-LSTM to deal with two problems: sequential image classification and text classification. | en |
| dc.description.sponsorship | Grant PID2019-108392GBI00 funded by MCIN/AEI/10.13039/501100011033, by CNPq (Proc. 301618/2019-4), FAPERGS (Proc. 19/2551-0001660), by Tracasa Instrumental and the Immigration Policy and Justice Department of the Government of Navarre and by the project VEGA 1/0267/21. | en |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.citation | Ferrero-Jaurrieta, M., Takac, Z., Fernandez, J., Horanska, L., Dimuro, G. P., Montes, S., Diaz, I., Bustince, H. (2022) VCI-LSTM: Vector choquet integral-based long short-term memory. IEEE Transactions on Fuzzy Systems, 1-14. https://doi.org/10.1109/TFUZZ.2022.3222035. | en |
| dc.identifier.doi | 10.1109/TFUZZ.2022.3222035 | |
| dc.identifier.issn | 1063-6706 | |
| dc.identifier.uri | https://academica-e.unavarra.es/handle/2454/45283 | |
| dc.language.iso | eng | en |
| dc.publisher | IEEE | en |
| dc.relation.ispartof | IEEE Transactions on Fuzzy Systems, 2022 | en |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI//PID2019-108392GBI00/ | |
| dc.relation.publisherversion | https://doi.org/10.1109/TFUZZ.2022.3222035 | |
| dc.rights | © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other work. | en |
| dc.rights.accessRights | info:eu-repo/semantics/openAccess | |
| dc.subject | Aggregation functions | en |
| dc.subject | Choquet integral | en |
| dc.subject | LSTM | en |
| dc.subject | Recurrent neural networks | en |
| dc.subject | Vector choquet integral | en |
| dc.title | VCI-LSTM: Vector choquet integral-based long short-term memory | en |
| dc.type | info:eu-repo/semantics/article | |
| dc.type.version | info:eu-repo/semantics/acceptedVersion | |
| dspace.entity.type | Publication | |
| relation.isAuthorOfPublication | 3e9cb4ee-2d64-47ff-9f40-d7519dc6cb0d | |
| relation.isAuthorOfPublication | 741321a5-40af-41aa-bacb-5da283dd18ab | |
| relation.isAuthorOfPublication | 4eb4bdb2-e3c9-46a2-983f-dfc0dfe20e54 | |
| relation.isAuthorOfPublication | 1bdd7a0e-704f-48e5-8d27-4486444f82c9 | |
| relation.isAuthorOfPublication.latestForDiscovery | 3e9cb4ee-2d64-47ff-9f40-d7519dc6cb0d |