A Wilson-Cowan reservoir computer for interpretable spatiotemporal vision.

Overview

1. Institute of Digital Technologies, Loughborough University London, 3 Lesney Avenue, Here East, Queen Elizabeth Olympic Park, E20 3BS London, UK
2. 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/ASIC deployment, positioning WC–RC as an interpretable, energy-aware reservoir for neuromorphic vision.

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/MSP.2012.2211477 and DOI: 10.48550/arXiv.1708.07747, respectively. The code will be shared upon request.

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://doi.org/10.1038/s41598-026-49359-5

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/s41467-026-74466-2 [code]

Neuromorphic hierarchical modular reservoirs.

Journal: Nature communications

In common: 4 references

[2] doi:10.1007/s11571-026-10512-5 [code]

Modeling the rhythmic complexity of professional drumming with an oscillation-driven reservoir computer.

Journal: Cognitive neurodynamics

In common: systems, 3 references

[3] doi:10.1038/s41586-026-10528-1 [code]

A critical initialization for biological neural networks.

Journal: Nature

In common: 3 references

[4] doi: [code]

Quantum-Tunnelling Oscillators for Cognitive Modelling and Neural Computation: Foundations, Machine-Vision Realisation and Applications

Journal: Entropy (Basel, Switzerland)

In common: 2 references

[5] doi:10.3390/biomimetics11070481 [code]

Task-State fMRI-Derived Whole-Brain Functional Topology-Constrained Spiking Neural Network with an Embedded Auditory Core Circuit for Speech Recognition.

Journal: Biomimetics (Basel, Switzerland)

In common: 2 references

[6] doi:10.1371/journal.pcbi.1014222 [code]

Neural population models for EEG: From Canonical models to alternative model structures.

Journal: PLoS computational biology

In common: 2 references

[7] doi:10.1038/s42003-026-09938-8 [code]

Representation Transfer via Invariant Input-driven Continuous Attractors for Fast Domain Adaptation.

Journal: Communications biology

In common: 2 references

[8] doi:10.1016/j.patter.2026.101563 [code]

Neural rhythms as priors of speech computations.

Journal: Patterns (New York, N.Y.)

In common: 2 references

[9] doi:10.3389/fncom.2026.1745836 [code]

Role of spinal sensorimotor circuits in triphasic muscle command: a simulation approach using goal exploration process.

Journal: Frontiers in computational neuroscience

In common: systems, 1 reference

[10] doi:10.1371/journal.pcbi.1014521 [code]

Whisker stimulation reinforces a resting-state network in the barrel cortex: Nested oscillations and avalanches.

Journal: PLoS computational biology

In common: systems, 1 reference

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.

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: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.