Title :
Wavelet networks as an alternative to neural networks
Author :
Ciuca, I. ; Ware, J.A.
Author_Institution :
Res. Inst. for Inf., Bucharest, Romania
Abstract :
The paper presents an alternative to the use of feedfoward neural networks as universal approximators. The alternative is based on the wavelet approximation theory of nonlinear functions. An algorithm from the evolutionary computation class is presented for wavelet network learning which as an optional facility, incorporates the capability for removing irrelevant features from input data in classification applications. The results of a dynamic process forecasting application are also presented
Keywords :
function approximation; learning (artificial intelligence); neural nets; wavelet transforms; classification; dynamic process forecasting; evolutionary computation; irrelevant features removal; nonlinear functions; universal approximators; wavelet approximation theory; wavelet networks; Approximation methods; Backpropagation algorithms; Evolutionary computation; Feedforward neural networks; Feedforward systems; Genetic algorithms; Genetic programming; Informatics; Neural networks; Principal component analysis;
Conference_Titel :
Emerging Technologies and Factory Automation Proceedings, 1997. ETFA '97., 1997 6th International Conference on
Conference_Location :
Los Angeles, CA
Print_ISBN :
0-7803-4192-9
DOI :
10.1109/ETFA.1997.616295
