Habituation based neural classifiers for spatio-temporal signals

Author

Stiles, Bryan W. ; Ghosh, Joydeep

Author_Institution

Dept. of Electr. & Comput. Eng., Texas Univ., Austin, TX, USA

Volume

5

fYear

1995

fDate

9-12 May 1995

Firstpage

3407

Abstract

Based on the habituation mechanism found in biological neural systems, novel dynamic neural networks are proposed for recognizing temporal patterns. The specific task considered in this paper is the classification of whale songs from passive sonar data, but the networks are also readily applicable to other temporal pattern recognition problems. The fact that the networks designed operate dynamically is important, because it makes the goal of real time data analysis possible

Keywords

aquaculture; biocommunications; encoding; neural nets; pattern classification; sonar signal processing; underwater sound; biological neural systems; dynamic neural networks; encoding; habituation based neural classifiers; habituation mechanism; passive sonar data; real time data analysis; spatio-temporal signals; temporal pattern recognition; whale songs classification; Biological information theory; Data analysis; Data preprocessing; Delay effects; Encoding; Equations; Neural networks; Pattern recognition; Sonar applications; Whales;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479717

Filename

479717