Artículo
Reservoir computing models based on spiking neural P systems for time series classification
Autor/es | Peng, Hong
Xiong, Xin Wu, Min Wang, Jun Yang, Qiang Orellana Martín, David Pérez Jiménez, Mario de Jesús |
Director | |
Departamento | Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial |
Fecha de publicación | 2024 |
Fecha de depósito | 2024-10-14 |
Publicado en |
|
Premios | Premio Mensual Publicación Científica Destacada de la US. Escuela Técnica Superior de Ingeniería Informática |
Resumen | Nonlinear spiking neural P (NSNP) systems are neural-like membrane computing models with nonlinear spiking mechanisms. Because of this nonlinear spiking mechanism, NSNP systems can show rich nonlinear dynamics. Reservoir ... Nonlinear spiking neural P (NSNP) systems are neural-like membrane computing models with nonlinear spiking mechanisms. Because of this nonlinear spiking mechanism, NSNP systems can show rich nonlinear dynamics. Reservoir computing (RC) is a novel recurrent neural network (RNN) and can overcome some shortcomings of traditional RNNs. Based on NSNP systems, we developed two RC variants for time series classification, RC-SNP and RC-RMS-SNP, which are without and integrated with reservoir model space (RMS), respectively. The two RC variants use NSNP systems as the reservoirs and can be easily implemented in the RC framework. The proposed two RC variants were evaluated on 17 benchmark time series classification datasets and compared with 16 state-of-the-art or baseline classification models. The comparison results demonstrate the effectiveness of the proposed two RC variants for time series classification tasks. |
Cita | Peng, H., Xiong, X., Wu, M., Wang, J., Yang, Q., Orellana Martín, D. y Pérez Jiménez, M.d.J. (2024). Reservoir computing models based on spiking neural P systems for time series classification. NEURAL NETWORKS, 169, 274-281. https://doi.org/10.1016/j.neunet.2023.10.041. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Reservoir computing models based ... | 544.8Kb | [PDF] | Ver/ | |