Constructing bifurcation diagram of reservoir computing

Xiaolu Chen, Tongfeng Weng, Zhuoming Ren and Huijie Yang

Physica A: Statistical Mechanics and its Applications, 2025, vol. 677, issue C

Abstract: We introduce a data-driven synchronization approach to construct the dynamical transition of reservoir computing. Specifically, we design a scheme composed of three identically coupled reservoir computers and each of them has learned the underlying chaotic information of a considered system. After realizing synchronization among these reservoir computers, we find that the bifurcation diagram of reservoir computing can be fully constructed by varying the leaking rate. Numerical results on several chaotic systems have further confirmed the effectiveness of our method. Our findings provide a new perspective on studying the internal dynamics of reservoir computing, paving the way for further practical applications.

Keywords: Data-driven model; Reservoir computer; Chaotic system; Synchronization; Bifurcation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378437125005667
Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:phsmap:v:677:y:2025:i:c:s0378437125005667

DOI: 10.1016/j.physa.2025.130914

Access Statistics for this article

Physica A: Statistical Mechanics and its Applications is currently edited by K. A. Dawson, J. O. Indekeu, H.E. Stanley and C. Tsallis

More articles in Physica A: Statistical Mechanics and its Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().