Ho, Charlotte YukFan, Ling, Bingo WingKuen, Lam, HakKeung and Nasir, Muhammad H. U. (2008) Global convergence and limit cycle behavior of weights of perceptron. IEEE Transactions on Neural networks, 19 (6). pp. 938947. ISSN 10459227
Full content URL: http://dx.doi.org/10.1109/TNN.2007.914187
Documents 

PDF
letter_chao_perceptron_bound.pdf  Whole Document Restricted to Repository staff only 217kB 
Item Type:  Article 

Item Status:  Live Archive 
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
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 On:  13 Jun 2010 11:36 
Repository Staff Only: item control page