Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

21

NN
2008
Springer

favoriteEmaildiscussreport

86views Neural Networks» more NN 2008»

Two k-winners-take-all networks with discontinuous activation functions

13 years 10 months ago

Two k-winners-take-all networks with discontinuous activation functions

Download www2.acae.cuhk.edu.hk

This paper presents two k-winners-take-all (k-WTA) networks with discontinuous activation functions. The k-WTA operation is first converted equivalently into linear and quadratic programming problems. Then two k-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 k-WTA operation in real time. Simulation results show the effectiveness and performance of the networks. c 2007 Elsevier Ltd. All rights reserved.

Qingshan Liu, Jun Wang

Real-time Traffic

K-WTA Operation | Neural Networks | NN 2008 | Quadratic Programming | Quadratic Programming Problems |

claim paper

Related Content

» Inserting G1 Discontinuities into Freeform Features for Aesthetic Design

» Two RuleBased BuildingBlock Architectures for PolicyBased Network Control

» On the Optimal Receiver Activation Function for DistanceBased Geographic Transmissions

» Distributed algorithms for reaching consensus on general functions

» Modified constrained learning algorithms incorporating additional functional constraints i...

» TwoWay Transmission Capacity of Wireless Adhoc Networks

» PiecewiseSmooth Dense Optical Flow via Level Sets

» Modeling Switching Activity Using Cascaded Bayesian Networks for Correlated Input Streams

» Modeling of multiresolution active network measurement timeseries

Post Info
More Details (n/a)

Added	14 Dec 2010
Updated	14 Dec 2010
Type	Journal
Year	2008
Where	NN
Authors	Qingshan Liu, Jun Wang

Comments (0)