Applications and extensions of unsupervised BCM projection pursuit for time-dependent classification

Author

Bachmann, Charles M. ; Luong, Dong Q. ; Moore, John W. ; Andreano, Keith J.

Author_Institution

US Naval Res. Lab., Washington, DC, USA

fYear

1993

fDate

6-9 Sep 1993

Firstpage

161

Lastpage

170

Abstract

Methods are developed for extending the unsupervised projection pursuit learning algorithm of Bienenstock, Cooper and Munro (BCM) (1982) to time-dependent classification problems. Recurrent and differential models of BCM which look for temporal structure in the evolution of high-dimensional inputs are described. Ordinary BCM obtains a 10db improvement in a noise tolerance study when compared with backward propagation (BP) for a database of simulated inverse synthetic aperature radar (ISAR) presentations. The recurrent and differential BCM models address the problem of classification from sequences of multiple presentations

Keywords

neural nets; pattern classification; unsupervised learning; database; differential models; high-dimensional inputs; input evolution; multiple presentation models; noise tolerance; recurrent models; simulated inverse synthetic aperature radar; temporal structure; time-dependent classification; unsupervised projection pursuit learning algorithm; Additive noise; Airborne radar; Databases; Ear; Laboratories; Neural networks; Noise figure; Noise robustness; Pursuit algorithms; Signal to noise ratio;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop

Conference_Location

Linthicum Heights, MD

Print_ISBN

0-7803-0928-6

Type

conf

DOI

10.1109/NNSP.1993.471873

Filename

471873