A one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all operation

Qingshan Liu; Jun Wang

doi:10.1109/IJCNN.2007.4370935

A one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all operation

Qingshan Liu
, Jun Wang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

This paper presents a one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all (kWTA) operation. The kWTA operation is first converted into an equivalent quadratic programming problem. Then a one-layer recurrent neural network is constructed. The neural network is guaranteed to be capable of performing the kWTA operation in real time. The stability and convergence of the neural network are proven by using Lyapunov and nonsmooth analysis methods. ©2007 IEEE.

Original language	English
Title of host publication	IEEE International Conference on Neural Networks - Conference Proceedings
Pages	84-89
DOIs	https://doi.org/10.1109/IJCNN.2007.4370935
Publication status	Published - 2007
Externally published	Yes
Event	2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, United States Duration: 12 Aug 2007 → 17 Aug 2007 https://ewh.ieee.org/conf/ijcnn/2007/ijcnn-2007.pdf

Publication series

Name
ISSN (Print)	1098-7576

Conference

Conference	2007 International Joint Conference on Neural Networks, IJCNN 2007
Place	United States
City	Orlando
Period	12/08/07 → 17/08/07
Internet address	https://ewh.ieee.org/conf/ijcnn/2007/ijcnn-2007.pdf

Access Output

10.1109/IJCNN.2007.4370935

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{c93c7125ed3843c8ae5468d92b38f730,

title = "A one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all operation",

abstract = "This paper presents a one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all (kWTA) operation. The kWTA operation is first converted into an equivalent quadratic programming problem. Then a one-layer recurrent neural network is constructed. The neural network is guaranteed to be capable of performing the kWTA operation in real time. The stability and convergence of the neural network are proven by using Lyapunov and nonsmooth analysis methods. {\textcopyright}2007 IEEE.",

author = "Qingshan Liu and Jun Wang",

year = "2007",

doi = "10.1109/IJCNN.2007.4370935",

language = "English",

isbn = "142441380",

pages = "84--89",

booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

note = "2007 International Joint Conference on Neural Networks, IJCNN 2007 ; Conference date: 12-08-2007 Through 17-08-2007",

url = "https://ewh.ieee.org/conf/ijcnn/2007/ijcnn-2007.pdf",

}

Liu, Q & Wang, J 2007, A one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all operation. in IEEE International Conference on Neural Networks - Conference Proceedings., 4370935, pp. 84-89, 2007 International Joint Conference on Neural Networks, IJCNN 2007, Orlando, Florida, United States, 12/08/07. https://doi.org/10.1109/IJCNN.2007.4370935

A one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all operation. / Liu, Qingshan; Wang, Jun.
IEEE International Conference on Neural Networks - Conference Proceedings. 2007. p. 84-89 4370935.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all operation

AU - Liu, Qingshan

AU - Wang, Jun

PY - 2007

Y1 - 2007

N2 - This paper presents a one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all (kWTA) operation. The kWTA operation is first converted into an equivalent quadratic programming problem. Then a one-layer recurrent neural network is constructed. The neural network is guaranteed to be capable of performing the kWTA operation in real time. The stability and convergence of the neural network are proven by using Lyapunov and nonsmooth analysis methods. ©2007 IEEE.

AB - This paper presents a one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all (kWTA) operation. The kWTA operation is first converted into an equivalent quadratic programming problem. Then a one-layer recurrent neural network is constructed. The neural network is guaranteed to be capable of performing the kWTA operation in real time. The stability and convergence of the neural network are proven by using Lyapunov and nonsmooth analysis methods. ©2007 IEEE.

UR - https://www.scopus.com/pages/publications/51749090434

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-51749090434&origin=recordpage

U2 - 10.1109/IJCNN.2007.4370935

DO - 10.1109/IJCNN.2007.4370935

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 142441380

SN - 9781424413805

SP - 84

EP - 89

BT - IEEE International Conference on Neural Networks - Conference Proceedings

T2 - 2007 International Joint Conference on Neural Networks, IJCNN 2007

Y2 - 12 August 2007 through 17 August 2007

ER -

A one-layer recurrent neural network with a unipolar hard-limiting activation function for k-winners-take-all operation

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this