WSOM: building adaptive wavelets with self-organizing maps

Author

Campos, Marcos M. ; Carpenter, Gail A.

Author_Institution

Dept. of Cognitive & Neural Syst., Boston Univ., MA, USA

Volume

1

fYear

1998

fDate

4-8 May 1998

Firstpage

763

Abstract

The WSOM (wavelet self-organizing map) model, a neural network for the creation of wavelet bases adapted to the distribution of input data, is introduced. The model provides an efficient online method to construct high-dimensional wavelet bases. Simulations of a 1D function approximation problem illustrate how WSOM adapts to non-uniformly distributed input data, outperforming the discrete wavelet transform. A speaker-independent vowel recognition benchmark task demonstrates how the model constructs high-dimensional bases using low-dimensional wavelets

Keywords

feedforward neural nets; function approximation; multilayer perceptrons; self-organising feature maps; speech recognition; wavelet transforms; 1D function approximation; adaptive wavelets; low-dimensional wavelets; self-organizing maps; speaker-independent vowel recognition benchmark task; wavelet bases; wavelet self-organizing map model; Acceleration; Algorithm design and analysis; Discrete wavelet transforms; Function approximation; Image coding; Neural networks; Self organizing feature maps; Signal analysis; Speech recognition; Wavelet analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.682377

Filename

682377