https://doi.org/10.1140/epjs/s11734-025-01704-x
Regular Article
Binary classification via spatiotemporal dynamics in reservoir computing rings of FitzHugh–Nagumo neurons
Federal Research Center A.V. Gaponov–Grekhov Institute of Applied Physics of the Russian Academy of Sciences, 46 Ulyanov Str., 603950, Nizhny Novgorod, Russia
Received:
31
March
2025
Accepted:
19
May
2025
Published online:
2
June
2025
Reservoir computing systems represent a prominent category of recurrent neural networks that combine sequential data processing capabilities with analytical tractability through nonlinear dynamical systems theory. These architectures can integrate diverse neural components such as rate-based units, spiking neurons, and oscillatory elements, with networks based on computational neuroscience models holding special significance as biologically inspired neuromorphic platforms. This work explores ring-structured configurations of FitzHugh–Nagumo neurons implemented as reservoir computing systems for binary classification. We establish fundamental connections between neural activity dynamics and computational performance, demonstrating how spatiotemporal patterns mediate the transformation of nonlinearly inseparable two-dimensional inputs into linearly separable representations. The analysis further investigates the comparative impact of rate-based versus temporal encoding strategies and systematically evaluates how variations in the dimensionality of feature vectors derived from system dynamics influence classification accuracy.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.