Share Email Print

Optical Engineering

Neural network adaptive wavelets for signal representation and classification
Author(s): Harold H. Szu; Brian A. Telfer; Shubha L. Kadambe
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Methods are presented for adaptively generating wavelet templates for signal representation and classification using neural networks. Different network structures and energy functions are necessary and are given for representation and classification. The idea is introduced of a "super-wavelet," a linear combination of wavelets that itself is treated as a wavelet. The super-wavelet allows the shape of the wavelet to adapt to a particular problem, which goes beyond adapting parameters of a fixed-shape wavelet. Simulations are given for 1-D signals, with the concepts extendable to imagery. Ideas are discussed for applying the concepts in the paper to phoneme and speaker recognition.

Paper Details

Date Published: 1 September 1992
PDF: 10 pages
Opt. Eng. 31(9) doi: 10.1117/12.59918
Published in: Optical Engineering Volume 31, Issue 9
Show Author Affiliations
Harold H. Szu, Naval Surface Warfare Ctr. (United States)
Brian A. Telfer, Naval Surface Warfare Ctr. (United States)
Shubha L. Kadambe, A.I. du Pont Institute (United States)

© SPIE. Terms of Use
Back to Top