Efficient training and improved performance of multilayer perceptron in pattern classification

Citation
Bb. Chaudhuri et U. Bhattacharya, Efficient training and improved performance of multilayer perceptron in pattern classification, NEUROCOMPUT, 34, 2000, pp. 11-27
Citations number
18
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
NEUROCOMPUTING
ISSN journal
09252312 → ACNP
Volume
34
Year of publication
2000
Pages
11 - 27
Database
ISI
SICI code
0925-2312(200009)34:<11:ETAIPO>2.0.ZU;2-U
Abstract
In pattern recognition problems, the convergence of backpropagation trainin g algorithm of a multilayer perceptron is slow if the concerned classes hav e complex decision boundary. To improve the performance, we propose a techn ique, which at first cleverly picks up samples near the decision boundary w ithout actually knowing the position of decision boundary. To choose the tr aining samples, a larger set of data with known class label is considered. For each datum, its k-neighbours are found. If the datum is near the decisi on boundary, then all of these k-neighbours would not come from the same cl ass. A training set, generated using this idea, results in quick and better convergence of the training algorithm. To get more symmetric neighbours, t he nearest centroid neighbourhood (Chaudhuri, Pattern Recognition Lett. 17 (1996) 11-17) is used. The performance of the technique has been tested on synthetic data as well as speech vowel data in two Indian languages. (C) 20 00 Elsevier Science B.V. All rights reserved.