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.
@article{arxiv.q-bio/0401001,
title = {K-Winners-Take-All Computation with Neural Oscillators},
author = {Wei Wang and Jean-Jacques E. Slotine},
journal= {arXiv preprint arXiv:q-bio/0401001},
year = {2007}
}