A Wilson-Cowan reservoir computer for interpretable spatiotemporal vision.
Overview
- Institute of Digital Technologies, Loughborough University London, 3 Lesney Avenue, Here East, Queen Elizabeth Olympic Park, E20 3BS London, UK
- Department of Physics, Loughborough University, Epinal Way, LE11 3TU Loughborough, UK
Abstract
We present a Wilson–Cowan reservoir computer (WC–RC) that treats a retinotopic excitatory–inhibitory neural field as a structured reservoir. Travelling waves and bounded oscillations provide an interpretable spatiotemporal basis, while a two-stage sampler (40 sites 200 steps) exports 8000 features per input—a reduction with unchanged integration cost. On MNIST and Fashion-MNIST, recurrent readouts trained on these features achieve strong performance within this fixed export budget: Att-LSTM reaches , while GRU and vanilla LSTM yield similar accuracies (all with tight Wilson 95% confidence intervals). A simple MLP readout performs markedly worse (), whereas a compact ridge classifier still attains non-trivial performance (), indicating that the exported WC–RC representation is partially linearly decodable but benefits further from temporal modelling. Selective suppression of lateral couplings () shows that reinstating wave dynamics improves recurrent models while degrading the MLP, supporting a functional role for propagating dynamics. A complementary neighbour-coupling ablation, implemented via a diffusion-like scaling factor , shows that increasing lateral spread beyond the baseline regime reduces late-time spatial variance and degrades recurrent-readout accuracy, indicating that useful computation depends on balanced wave dynamics rather than maximal smoothing. At matched exported-feature and readout budgets, ESN baselines underperform (), whereas compact CNNs achieve higher accuracy but with larger parameter and MAC budgets and without wave interpretability. Supplementary analyses confirm numerical fidelity and relate performance gains to propagation coherence. We outline a fixed-point streaming-convolution mapping for FPGA/
Reproduced under the paper's license (CC BY), from the paper cited above.
Code
The paper says that its authors' code is available on request: it was not published with the paper, so there is nothing to verify.
The paper's code and data availability statement is in the Data section.
Tracing map
A tracing map links a paper to the code its authors published: this paper has none (its code is available on request), so it has no map.
Data
No dataset and no data link were found in the paper.
Data availability
The datasets used for the simulations are the MNIST handwritten digits dataset34 and the Fashion-MNIST dataset35, both published open-source by their respective authors as declared in DOI: 10.1109/
Reproduced under the paper's license (CC BY), from the paper cited above.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 1, 28 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 10 keywords, 1 funder, 24 references.
Cite
This paper
Gabayre, S. A., Savel’ev, S., De Silva, V., Illeperuma, M., & Shi, X. (2026). A Wilson-Cowan reservoir computer for interpretable spatiotemporal vision. Scientific reports, 16(1), 20484. https://
BibTeX
@article{gabayre2026wils
author = {Gabayre, Sharmarke A and Savel’ev, Sergey and De Silva, Varuna and Illeperuma, Mindula and Shi, Xiyu},
title = {{A Wilson-Cowan reservoir computer for interpretable spatiotemporal vision}},
journal = {Scientific reports},
year = {2026},
month = may,
volume = {16},
number = {1},
pages = {20484},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/
url = {https://
pmid = {42082555},
pmcid = {PMC13328669}
}
RIS
TY - JOUR
AU - Gabayre, Sharmarke A
AU - Savel’ev, Sergey
AU - De Silva, Varuna
AU - Illeperuma, Mindula
AU - Shi, Xiyu
TI - A Wilson-Cowan reservoir computer for interpretable spatiotemporal vision
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/
VL - 16
IS - 1
SP - 20484
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1038/
"type": "article-journal",
"title": "A Wilson-Cowan reservoir computer for interpretable spatiotemporal vision",
"container-title": "Scientific reports",
"author": [
{
"family": "Gabayre",
"given": "Sharmarke A"
},
{
"family": "Savel’ev",
"given": "Sergey"
},
{
"family": "De Silva",
"given": "Varuna"
},
{
"family": "Illeperuma",
"given": "Mindula"
},
{
"family": "Shi",
"given": "Xiyu"
}
],
"container-title-short":
"volume": "16",
"issue": "1",
"page": "20484",
"DOI": "10.1038/
"PMID": "42082555",
"PMCID": "PMC13328669",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
4
]
]
}
}
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1038/s41467-025-62151-9 [code]
- Artificial transneurons emulate neuronal activity in different areas of brain cortex.Journal: Nature communicationsIn common: systems, 1 reference, author Sergey Savel’ev
- [2] doi:10.1038/s41467-026-74466-2 [code]
- Neuromorphic hierarchical modular reservoirs.Journal: Nature communicationsIn common: 4 references
- [3] doi:10.1007/s11571-026-10512-5 [code]
- Modeling the rhythmic complexity of professional drumming with an oscillation-driven reservoir computer.Journal: Cognitive neurodynamicsIn common: systems, 3 references
- [4] doi:10.1016/j.patter.2025.101457 [code]
- Evolving reservoir computers reveal bidirectional coupling between predictive power and emergent dynamics.Journal: Patterns (New York, N.Y.)In common: 3 references
- [5] doi:10.3390/biomimetics10050341 [code]
- The &
lt;i& gt;Drosophila& lt;/ i& gt; Connectome as a Computational Reservoir for Time-Series Prediction. Journal: Biomimetics (Basel, Switzerland)In common: 3 references - [6] doi:10.1038/s41467-025-67137-1 [code]
- Reshaping reservoirs with unsupervised Hebbian adaptation.Journal: Nature communicationsIn common: 3 references
- [7] doi:10.1038/s41467-026-70920-3 [code]
- Intrinsic stabilization of synaptic plasticity improves learning and robustness in artificial neural networks.Journal: Nature communicationsIn common: 3 references
- [8] doi:10.1038/s41467-024-44900-4 [code]
- Connectome-based reservoir computing with the conn2res toolbox.Journal: Nature communicationsIn common: 3 references
- [9] doi:10.1038/s41586-026-10528-1 [code]
- A critical initialization for biological neural networks.Journal: NatureIn common: 3 references
- [10] doi:10.1038/s41598-026-42971-5 [code]
- Adaptive state-feedback echo state networks for temporal sequence learning.Journal: Scientific reportsIn common: 3 references
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
