Reservoir computing models based on spiking neural P systems for time series classification

doi:10.1016/j.neunet.2023.10.041

Reservoir computing models based on spiking neural P systems for time series classification

2024-01-01

18

PRE

AI

David Orellana-Martín

M

Mario J. Pérez-Jímenez

DOI：10.1016/j.neunet.2023.10.041

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Recurrent neural networks

Reservoir computing

Nonlinear spiking neural P systems

Time series classification

Reservoir computing models based on spiking neural P systems for time series classification

Abstract

Journal

Organization