Strict Generalization in Multilayered Perceptron Networks

Authors:
Debrup Chakraborty;Nikhil R. Pal
Affiliations:
Computer Science Department, CINVESTAV-IPN, Av. IPN No. 2508, Col. San Pedro Zacatenco, Mexico, D.F. 07360, Mexico;Electronics and Communication Sciences Unit, Indian Statistical Institute, 203 B.T. Road, Calcutta 700108, India
Venue:
IFSA '07 Proceedings of the 12th international Fuzzy Systems Association world congress on Foundations of Fuzzy Logic and Soft Computing
Year:
2007

Citing 3
Cited 0

Fuzzy Models and Algorithms for Pattern Recognition and Image Processing

Fuzzy Models and Algorithms for Pattern Recognition and Image Processing
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
A novel training scheme for multilayered perceptrons to realize proper generalization and incremental learning

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Typically the response of a multilayered perceptron (MLP) network on points which are far away from the boundary of its training data is not very reliable. When test data points are far away from the boundary of its training data, the network should not make any decision on these points. We propose a training scheme for MLPs which tries to achieve this. Our methodology trains a composite network consisting of two subnetworks : a mapping network and a vigilance network. The mapping network learns the usual input-output relation present in the data and the vigilance network learns a decision boundary and decides on which points the mapping network should respond. Though here we propose the methodology for multilayered perceptrons, the philosophy is quite general and can be used with other learning machines also.