dorsal/arxiv
View SchemaReservoir computing from collective dynamics of active colloidal oscillators
| Authors | Veit-Lorenz Heuthe, Lukas Seemann, Samuel Tovey, Clemens Bechinger |
|---|---|
| Categories | |
| ArXiv ID | 2601.05767vv1 |
| URL | https://arxiv.org/abs/2601.05767 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
Physical reservoir computing is a computational framework that offers an energy- and computation-efficient alternative to conventional training of neural networks. In reservoir computing, input signals are mapped into the high-dimensional dynamics of a nonlinear system, and only a simple readout layer is trained. In most physical implementations, the interactions that give rise to the dynamics cannot be tuned directly and high dimensionality is typically achieved through time-multiplexing, which can limit flexibility and efficiency. Here we introduce a reservoir composed of hundreds of hydrodynamically coupled active colloidal oscillators forming a fully parallel physical reservoir and whose coupling strength and fading-memory time can be tuned in situ. The collective dynamics of the active oscillators allow accurate predictions of chaotic time series from single reservoir readouts without time-multiplexing. We further demonstrate real-time detection of subtle hidden anomalies that preserve all instantaneous statistical properties of the signal yet disrupt its underlying temporal correlations. These results establish interacting active colloids as a reconfigurable platform for physical computation and edge-integrated intelligent sensing for model-free detection of irregularities in complex time signals.
{
"annotation_id": "5b0440b8-e2cd-42ba-a10f-db4e550bd2e7",
"date_created": "2026-02-17T05:53:04.319000Z",
"date_modified": "2026-02-17T05:53:04.319000Z",
"file_hash": "7207ace712a69200ead855583e816f0094f4ab145b8de17d11d3fed23e1d924b",
"private": false,
"record": {
"abstract": "Physical reservoir computing is a computational framework that offers an energy- and computation-efficient alternative to conventional training of neural networks. In reservoir computing, input signals are mapped into the high-dimensional dynamics of a nonlinear system, and only a simple readout layer is trained. In most physical implementations, the interactions that give rise to the dynamics cannot be tuned directly and high dimensionality is typically achieved through time-multiplexing, which can limit flexibility and efficiency. Here we introduce a reservoir composed of hundreds of hydrodynamically coupled active colloidal oscillators forming a fully parallel physical reservoir and whose coupling strength and fading-memory time can be tuned in situ. The collective dynamics of the active oscillators allow accurate predictions of chaotic time series from single reservoir readouts without time-multiplexing. We further demonstrate real-time detection of subtle hidden anomalies that preserve all instantaneous statistical properties of the signal yet disrupt its underlying temporal correlations. These results establish interacting active colloids as a reconfigurable platform for physical computation and edge-integrated intelligent sensing for model-free detection of irregularities in complex time signals.",
"arxiv_id": "2601.05767",
"authors": [
"Veit-Lorenz Heuthe",
"Lukas Seemann",
"Samuel Tovey",
"Clemens Bechinger"
],
"categories": [
"cond-mat.soft",
"physics.app-ph"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Reservoir computing from collective dynamics of active colloidal oscillators",
"url": "https://arxiv.org/abs/2601.05767",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "e80b6a7f-5b04-40c2-ac1e-47c63908c87c",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}