A Review of Spiking Neural Networks for Reservoir Computing in Chaotic Time-Series Prediction
International Journal of Scientific Research in Science, Engineering and Technology · 23.05.2026 · 13 (3) · 201-208
DOI: 10.32628/ijsrset2613325 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 23.05.2026. Verfasst von Lokhande Gauri Digambar und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Reservoir computing has emerged as an efficient approach for processing temporal data using recurrent neural networks with simplified training mechanisms. In this work, a simulation-based spiking neural network (SNN) architecture is proposed for low-power reservoir computing and chaotic time-series prediction. The system utilizes a recurrent reservoir composed of randomly connected spiking neurons that dynamically process temporal inputs while maintaining fixed internal weights. The Mackey–Glass chaotic time-series dataset is used to evaluate the prediction capability of the proposed model. The input signal is sequentially fed into the reservoir network, where nonlinear neuron dynamics generate rich internal state representations. A linear readout layer trained using pseudo-inverse regression maps these reservoir states to the predicted output signal. This paper presents a comprehensive review of spiking neural networks (SNNs) applied to reservoir computing for chaotic time-series prediction. Recent studies from 2022–2026 are analyzed, focusing on neuron models, reservoir architectures, and physical implementations. The Mackey–Glass time series is widely used as a benchmark dataset in these works. Comparative analysis highlights improvements in prediction accuracy, computational efficiency, and energy optimization. The review also identifies key research gaps, including limited real-world deployment and lack of standardized evaluation metrics, and outlines future research directions in neuromorphic computing.
Zitieren
APA
Digambar, L. G., Khot, M. J. S., N, D. D. S., & Rajesh, D. D. A. (2026). A Review of Spiking Neural Networks for Reservoir Computing in Chaotic Time-Series Prediction. International Journal of Scientific Research in Science, Engineering and Technology, 13(3), 201-208. https://doi.org/10.32628/ijsrset2613325
Vancouver
Digambar LG, Khot MJS, N DDS, Rajesh DDA. A Review of Spiking Neural Networks for Reservoir Computing in Chaotic Time-Series Prediction. International Journal of Scientific Research in Science, Engineering and Technology. 2026;13(3):201-208. doi:10.32628/ijsrset2613325
BibTeX
@article{Digambar2026,
author = {Digambar, Lokhande Gauri and Khot, Mrs. Jayashri Santosh and N, Dr. Divekar S. and Rajesh, Dr. Date Archana},
title = {A Review of Spiking Neural Networks for Reservoir Computing in Chaotic Time-Series Prediction},
journal = {International Journal of Scientific Research in Science, Engineering and Technology},
year = {2026},
volume = {13},
number = {3},
pages = {201--208},
doi = {10.32628/ijsrset2613325}
}
EUVIMED