A General Mean-Based Iterative Winner-Take-All Neural Network

Jar Ferr Yang; Chi Ming Chen; Wen Chung Wang; Jau Yien Lee

doi:10.1109/72.363454

A General Mean-Based Iterative Winner-Take-All Neural Network

Jar Ferr Yang, Chi Ming Chen, Wen Chung Wang, Jau Yien Lee

Institute of Computer and Communication Engineering

Research output: Contribution to journal › Article › peer-review

19 Citations (Scopus)

Abstract

In this paper, a new iterative winner-take-all (WTA) neural network is developed and analyzed. The proposed WTA neural net with one-layer structure is established under the concept of the statistical mean. For three typical distributions of initial activations, the convergence behaviors of the existing and the proposed WTA neural nets are evaluated by theoretical analyses and Monte Carlo simulations. We found that the suggested WTA neural network on average requires fewer than Log2 M iterations to complete a WTA process for the three distributed inputs, where M is the number of competitors. Furthermore, the fault tolerances of the iterative WTA nets are analyzed and simulated. From the view points of convergence speed, hardware complexity, and robustness to the errors, the proposed WTA is suitable for various applications.

Original language	English
Pages (from-to)	14-24
Number of pages	11
Journal	IEEE Transactions on Neural Networks
Volume	6
Issue number	1
DOIs	https://doi.org/10.1109/72.363454
Publication status	Published - 1995 Jan

All Science Journal Classification (ASJC) codes

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/72.363454

Cite this

@article{743c5a3e909845d6b5362249529b0d6e,

title = "A General Mean-Based Iterative Winner-Take-All Neural Network",

abstract = "In this paper, a new iterative winner-take-all (WTA) neural network is developed and analyzed. The proposed WTA neural net with one-layer structure is established under the concept of the statistical mean. For three typical distributions of initial activations, the convergence behaviors of the existing and the proposed WTA neural nets are evaluated by theoretical analyses and Monte Carlo simulations. We found that the suggested WTA neural network on average requires fewer than Log2 M iterations to complete a WTA process for the three distributed inputs, where M is the number of competitors. Furthermore, the fault tolerances of the iterative WTA nets are analyzed and simulated. From the view points of convergence speed, hardware complexity, and robustness to the errors, the proposed WTA is suitable for various applications.",

author = "Yang, {Jar Ferr} and Chen, {Chi Ming} and Wang, {Wen Chung} and Lee, {Jau Yien}",

note = "Funding Information: Manuscript received August 6, 1992; revised March 6, 1993. This work was supported by Computer & Communication Research Laboratories, Industrial Technology Research Institute under Contract IRTI-79-2939, Taiwan, ROC. The authors are with the Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan 70101, Republic of China. IEEE Log Number 9208991.",

year = "1995",

month = jan,

doi = "10.1109/72.363454",

language = "English",

volume = "6",

pages = "14--24",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

number = "1",

}

TY - JOUR

T1 - A General Mean-Based Iterative Winner-Take-All Neural Network

AU - Yang, Jar Ferr

AU - Chen, Chi Ming

AU - Wang, Wen Chung

AU - Lee, Jau Yien

N1 - Funding Information: Manuscript received August 6, 1992; revised March 6, 1993. This work was supported by Computer & Communication Research Laboratories, Industrial Technology Research Institute under Contract IRTI-79-2939, Taiwan, ROC. The authors are with the Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan 70101, Republic of China. IEEE Log Number 9208991.

PY - 1995/1

Y1 - 1995/1

N2 - In this paper, a new iterative winner-take-all (WTA) neural network is developed and analyzed. The proposed WTA neural net with one-layer structure is established under the concept of the statistical mean. For three typical distributions of initial activations, the convergence behaviors of the existing and the proposed WTA neural nets are evaluated by theoretical analyses and Monte Carlo simulations. We found that the suggested WTA neural network on average requires fewer than Log2 M iterations to complete a WTA process for the three distributed inputs, where M is the number of competitors. Furthermore, the fault tolerances of the iterative WTA nets are analyzed and simulated. From the view points of convergence speed, hardware complexity, and robustness to the errors, the proposed WTA is suitable for various applications.

AB - In this paper, a new iterative winner-take-all (WTA) neural network is developed and analyzed. The proposed WTA neural net with one-layer structure is established under the concept of the statistical mean. For three typical distributions of initial activations, the convergence behaviors of the existing and the proposed WTA neural nets are evaluated by theoretical analyses and Monte Carlo simulations. We found that the suggested WTA neural network on average requires fewer than Log2 M iterations to complete a WTA process for the three distributed inputs, where M is the number of competitors. Furthermore, the fault tolerances of the iterative WTA nets are analyzed and simulated. From the view points of convergence speed, hardware complexity, and robustness to the errors, the proposed WTA is suitable for various applications.

UR - http://www.scopus.com/inward/record.url?scp=0029207694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029207694&partnerID=8YFLogxK

U2 - 10.1109/72.363454

DO - 10.1109/72.363454

M3 - Article

AN - SCOPUS:0029207694

VL - 6

SP - 14

EP - 24

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 1

ER -

A General Mean-Based Iterative Winner-Take-All Neural Network

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this