Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
404683 | Neural Networks | 2008 | 8 Pages |
Abstract
This paper presents two kk-winners-take-all (kk-WTA) networks with discontinuous activation functions. The kk-WTA operation is first converted equivalently into linear and quadratic programming problems. Then two kk-winners-take-all networks are designed based on the linear and quadratic programming formulations. The networks are theoretically guaranteed to be capable of performing the kk-WTA operation in real time. Simulation results show the effectiveness and performance of the networks.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Qingshan Liu, Jun Wang,