Global convergence and limit cycle behavior of weights of perceptron

Ho, Charlotte Yuk-Fan and Ling, Bingo Wing-Kuen and Lam, Hak-Keung and Nasir, Muhammad H. U. (2008) Global convergence and limit cycle behavior of weights of perceptron. IEEE Transactions on Neural networks, 19 (6). pp. 938-947. ISSN 1045-9227

Documents
letter_chao_perceptron_bound.pdf
[img]
[Download]
Request a copy
[img] PDF
letter_chao_perceptron_bound.pdf - Whole Document
Restricted to Repository staff only

217kB

Official URL: http://dx.doi.org/10.1109/TNN.2007.914187

Abstract

In this paper, it is found that the weights of a perceptron are bounded for all initial weights if there exists a nonempty set of initial weights that the weights of the perceptron are bounded. Hence, the boundedness condition of the weights of the perceptron is independent of the initial weights. Also, a necessary and sufficient condition for the weights of the perceptron exhibiting a limit cycle behavior is derived. The range of the number of updates for the weights of the perceptron required to reach the limit cycle is estimated. Finally, it is suggested that the perceptron exhibiting the limit cycle behavior can be employed for solving a recognition problem when downsampled sets of bounded training feature vectors are linearly separable. Numerical computer simulation results show that the perceptron exhibiting the limit cycle behavior can achieve a better recognition performance compared to a multilayer perceptron

Item Type:Article
Additional Information:In this paper, it is found that the weights of a perceptron are bounded for all initial weights if there exists a nonempty set of initial weights that the weights of the perceptron are bounded. Hence, the boundedness condition of the weights of the perceptron is independent of the initial weights. Also, a necessary and sufficient condition for the weights of the perceptron exhibiting a limit cycle behavior is derived. The range of the number of updates for the weights of the perceptron required to reach the limit cycle is estimated. Finally, it is suggested that the perceptron exhibiting the limit cycle behavior can be employed for solving a recognition problem when downsampled sets of bounded training feature vectors are linearly separable. Numerical computer simulation results show that the perceptron exhibiting the limit cycle behavior can achieve a better recognition performance compared to a multilayer perceptron
Keywords:Neural networks, Perceptron
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
G Mathematical and Computer Sciences > G420 Networks and Communications
Divisions:College of Science > School of Computer Science
ID Code:2686
Deposited By: Bev Jones
Deposited On:13 Jun 2010 11:36
Last Modified:13 Mar 2013 08:39

Repository Staff Only: item control page