Fuzzy ARTMAP network with evolutionary learning

Author

Ramuhalli, P. ; Polikar, R. ; Udpa, L. ; Udpa, S.S.

Author_Institution

Dept. of Electr. Eng. & Comput. Eng., Iowa State Univ., Ames, IA, USA

Volume

6

fYear

2000

fDate

6/22/1905 12:00:00 AM

Firstpage

3466

Abstract

Neural networks, particularly the multilayer perceptron, have been used extensively in automated signal classification systems with classification accuracy as the figure of merit. Three important issues that can enhance the utility of these systems are (i) incremental learning, (ii) confidence or reliability measures and (iii) performance improvement through continual learning. This paper investigates these issues using a fuzzy ARTMAP network. A hypothesis testing based algorithm is developed for computing reliability measures, which are fed back to the network for retraining and performance improvement. Implementation results on ultrasonic data are presented

Keywords

fuzzy neural nets; inspection; learning (artificial intelligence); multilayer perceptrons; signal classification; ultrasonic materials testing; automated signal classification systems; classification accuracy; confidence measures; evolutionary learning; fuzzy ARTMAP network; hypothesis testing based algorithm; incremental learning; multilayer perceptron; neural networks; nondestructive evaluation; performance improvement; reliability measures; retraining; ultrasonic data; ultrasonic inspection; Computer networks; Fuzzy neural networks; Fuzzy systems; Neural networks; Pattern classification; Random variables; Reliability engineering; Testing; Time measurement; Ultrasonic variables measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-6293-4

Type

conf

DOI

10.1109/ICASSP.2000.860147

Filename

860147