ON THE RATE OF CONVERGENCE OF PERCEPTRON LEARNING

Authors
BHATTACHARYA U PARUI SK
Citation
U. Bhattacharya et Sk. Parui, ON THE RATE OF CONVERGENCE OF PERCEPTRON LEARNING, Pattern recognition letters, 16(5), 1995, pp. 491-497
Citations number
5
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence
Journal title
Pattern recognition letters → ACNP
ISSN journal
01678655
Volume
16
Issue
5
Year of publication
1995
Pages
491 - 497
Database
ISI
SICI code
0167-8655(1995)16:5<491:OTROCO>2.0.ZU;2-0
Abstract
In neural networks, convergence in iterative learning is a common prob lem. For fast learning one should be able to control the rate of conve rgence. In the present paper, the single-layer perceptron model for tw o classes is considered where the rate of convergence is studied with several choices of the gain term in the updation rule. Experimental re sults on a number of two-class problems are reported.