Heterogeneous-speed recurrent neural networks: Multi-timescale dynamics for fast and stable motion perception

Xiaoteng Zhang, Shan Lu, Zhiyuan Ning, Yingjie Zhu and Li Shi

Chaos, Solitons & Fractals, 2026, vol. 210, issue P1

Abstract: Perception in dynamic environments demands both speed for detecting transients and stability for integrating noisy evidence over time. We propose a general dynamical framework that links multi-timescale, delay-coupled neural dynamics to an interpretable, trainable architecture for motion perception. Starting from extracellular recordings, neurons are stratified by spike width and firing rate into narrow-, intermediate-, and broad-spiking classes, revealing distinct latencies and durations to moving versus looming stimuli. These observations motivate a continuous-time rate model with heterogeneous time constants, explicit input/recurrent delays, and a cluster-level divisive normalization that bounds population activity. We further analyze sufficient conditions under which the delayed dynamics are well posed and bounded, and show how timescale separation gives rise to an interpretable fast/slow decomposition. Via delay-consistent discretization, the model yields a Heterogeneous-Speed RNN (HS-RNN) whose blocks map one-to-one to the mechanistic terms, enabling interpretable ablations. On motion-sequence classification and synthetic object-detection tasks, HS-RNN achieves superior performance to the compared recurrent models, whereas on static-sequence tasks its advantage is much less pronounced. Hidden states reproduce physiological fingerprints – shorter latencies and stronger transients for moving stimuli alongside longer sustained responses – demonstrating biological consistency. Although validated on the avian Entopallium-Mesopallium Ventrolaterale pathway, the framework is modality- and species-agnostic, offering a principled route from circuit dynamics to robust sequence models.

Keywords: Multi-timescale dynamics; Delay systems; Cluster normalization; Motion perception; Recurrent neural networks; Biological inspiration (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960077926007101
Full text for ScienceDirect subscribers only

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:chsofr:v:210:y:2026:i:p1:s0960077926007101

DOI: 10.1016/j.chaos.2026.118569

Access Statistics for this article

Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros

More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. ().