dorsal/arxiv
View SchemaK-Winners-Take-All Computation with Neural Oscillators
| Authors | Wei Wang, Jean-Jacques E. Slotine |
|---|---|
| Categories | |
| ArXiv ID | q-bio/0401001 |
| URL | https://arxiv.org/abs/q-bio/0401001 |
Abstract
Artificial spike-based computation, inspired by models of computation in the central nervous system, may present significant performance advantages over traditional methods for specific types of large scale problems. This paper describes very simple network architectures for k-winners-take-all and soft-winner-take-all computation using neural oscillators. Fast convergence is achieved from arbitrary initial conditions, which makes the networks particularly suitable to track time-varying inputs.
{
"annotation_id": "447fbea1-f485-46e9-bbd8-35c15943d453",
"date_created": "2026-03-02T18:01:31.612000Z",
"date_modified": "2026-03-02T18:01:31.612000Z",
"file_hash": "beb721efdabac811c8a778c145ff4650f026509da5767f3b6585d56ab2920ce2",
"private": false,
"record": {
"abstract": "Artificial spike-based computation, inspired by models of computation in the\ncentral nervous system, may present significant performance advantages over\ntraditional methods for specific types of large scale problems. This paper\ndescribes very simple network architectures for k-winners-take-all and\nsoft-winner-take-all computation using neural oscillators. Fast convergence is\nachieved from arbitrary initial conditions, which makes the networks\nparticularly suitable to track time-varying inputs.",
"arxiv_id": "q-bio/0401001",
"authors": [
"Wei Wang",
"Jean-Jacques E. Slotine"
],
"categories": [
"q-bio.NC"
],
"title": "K-Winners-Take-All Computation with Neural Oscillators",
"url": "https://arxiv.org/abs/q-bio/0401001"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "6b4f8cc0-bb73-4697-b1c2-4d67e03006c2",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}