dc.contributor.author | Lucas Hernáez, Sergio | |
dc.contributor.author | Portillo Pérez, Eva | |
dc.date.accessioned | 2024-05-15T16:08:53Z | |
dc.date.available | 2024-05-15T16:08:53Z | |
dc.date.issued | 2024-05 | |
dc.identifier.citation | Neural Networks 173 : (2024) // Article ID 106171 | es_ES |
dc.identifier.issn | 0893-6080 | |
dc.identifier.issn | 1879-2782 | |
dc.identifier.uri | http://hdl.handle.net/10810/67959 | |
dc.description.abstract | piking Neural Networks (SNN) are recognised as well-suited for processing spatiotemporal information with ultra-low energy consumption. However, proposals based on SNN for classification tasks are more common than for forecasting problems. In this sense, this paper presents a new general training methodology for univariate time-series forecasting based on SNN. The methodology is focused on one-step ahead forecasting problems and combines a PulseWidth Modulation based encoding–decoding algorithm with a Surrogate Gradient method as supervised training algorithm. In order to validate the generality of the presented methodology sine-wave, 3 UCI and 1 available real-world datasets are used. The results show very satisfactory forecasting results () regardless of the characteristics of the dataset or the application field. In addition, weights can be initialised just once to achieve robust results, boosting the advantages of computational and energy cost of SNN. | es_ES |
dc.description.sponsorship | This work has been supported by grant IT1726- 22 funded by the Basque Government, grant PID2020-112667RB- I00 funded by MCIN/AEI/10.13039/501100011033, NEUROTIP project funded by Programme Euskampus Missions Euskampus Foundation, and grant PIBA_2020_1_0008 funded by Department of Education of the Basque Government. Open Access funding provided by University of Basque Country . | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | Elsevier | es_ES |
dc.relation | info:eu-repo/grantAgreement/MICINN/PID2020-112667RB-I00 | es_ES |
dc.rights | info:eu-repo/semantics/openAccess | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | * |
dc.subject | spiking neural network | es_ES |
dc.subject | forecasting | es_ES |
dc.subject | supervised learning | es_ES |
dc.subject | PWM based encoding–decoding algorithm | es_ES |
dc.subject | surrogate gradient | es_ES |
dc.title | Methodology based on spiking neural networks for univariate time-series forecasting | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.rights.holder | © 2024 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-
nc-nd/4.0/). | es_ES |
dc.rights.holder | Atribución-NoComercial-SinDerivadas 3.0 España | * |
dc.relation.publisherversion | https://www.sciencedirect.com/science/article/pii/S0893608024000959 | es_ES |
dc.identifier.doi | 10.1016/j.neunet.2024.106171 | |
dc.departamentoes | Ingeniería de sistemas y automática | es_ES |
dc.departamentoeu | Sistemen ingeniaritza eta automatika | es_ES |