A general mean-based iterative winner-take-all neural network

Author

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

Author_Institution

Dept. of Electr. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan

Volume

6

Issue

1

fYear

1995

fDate

1/1/1995 12:00:00 AM

Firstpage

14

Lastpage

24

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 Log₂M 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

Keywords

computational complexity; iterative methods; neural nets; Monte Carlo simulations; WTA neural nets; convergence; error robustness; hardware complexity; mean-based iterative winner-take-all neural network; one-layer structure; statistical mean; Analytical models; Computer aided manufacturing; Convergence; Fault tolerance; Hardware; Multi-layer neural network; Neural networks; Neurons; Resonance; Robustness;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.363454

Filename

363454