Previous [1] [2] [3] [4] [5] [6] [7] [8] [9] [10]

Journal of Inforamtion Science and Engineering, Vol.18 No.2, pp.211-222 (March 2002)

A Fast Winner-Take-All Neural Networks
With eht Dynamic Ratio

Chi-Ming Chen, Ming-Hung Hsu and Tien-Yo Wang
College of Knowledge Economy
Aletheia University
Tainan, 721 Taiwan

In this paper, we propose a fast winner-take-all (WTA) neural network. The fast winner-take-all neural network with the dynamic ratio in mutual-inhibition is developed from the general mean-based neural network (GEMNET), which adopts the mean of the active neurons as the threshold of mutual inhibition. Furthermore, the other winner-take-all neural network enhances the convergence speed to become a decimal system. The proposed WTA neural networks statistically achieve the large ratio of mutual inhibition. The new WTA Neural Networks converge faster than the existing WTA neural networks for a large number of competitors based on both theoretical analyses and simulation results.

Keywords: winner-take-all, neural network, convergence speed, decimal system, mutual inhibition

Full Text () Retrieve PDF document (200203_04.pdf)

Received July 29, 1999; revised March 30 & September 6, 2000; accepted October 26, 2000.
Communicated by Chuen-Tsai Sun.