https://doi.org/10.1140/epjs/s11734-025-02077-x
Regular Article
LAMRC: a locally active memristor-based chaotic system with diverse dynamics for reservoir computing
1
College of Computer Science and Artificial Intelligence, Southwest Minzu University, 610225, Chengdu, China
2
College of Artificial Intelligence, Southwest University, 400715, Chongqing, China
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
15
April
2025
Accepted:
18
November
2025
Published online:
6
February
2026
Abstract
The rich and diverse dynamics can endow chaotic systems with great flexibility, such as the edge of chaos. The diverse dynamics of chaotic systems caused by locally active memristors (LAMs) has been widely studied in the continuous model. However, discrete memristors (DMs) have not attracted much attention in this regard. Compared with continuous memristors (CMs), DMs are easier to implement on the hardware platform and conducive to the hybrid design of digital and analog. In this paper, we present a locally active discrete memristor (LADM) model and construct an improved 2D sine map with the LADM. The LADM-based sine map exhibits rich dynamical behaviors, including Feigenbaum trees, reverse bubbles, etc. In addition, a hardware platform is developed to implement the LADM-based chaotic map, with the phase portraits of four distinct cases being captured and visualized through an oscilloscope. Finally, we apply the LADM-based map to RC for the first time and verify its performance with two data sets from the real world. Experimental findings demonstrate that employing the LADM-based map as a reservoir significantly enhances reservoir computing (RC) performance, providing a new idea for future data processing.
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 2026
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.
