articleTop 1% cited

Wavelet networks

IEEE Transactions on Neural Networks · 1992 · Vol. 3(6) · pp. 889–898

Q. Zhang✉(Thermal Systems Technology (Sweden))Albert Benveniste(Institut de Recherche en Informatique et Systèmes Aléatoires)

View via DOI Publisher page

Abstract

A wavelet network concept, which is based on wavelet transform theory, is proposed as an alternative to feedforward neural networks for approximating arbitrary nonlinear functions. The basic idea is to replace the neurons by ;wavelons', i.e., computing units obtained by cascading an affine transform and a multidimensional wavelet. Then these affine transforms and the synaptic weights must be identified from possibly noise corrupted input/output data. An algorithm of backpropagation type is proposed for wavelet network training, and experimental results are reported.

Neural Networks and Applications Image and Signal Denoising Methods Blind Source Separation TechniquesBackpropagationWavelet transformWaveletComputer scienceAffine transformationLifting schemeStationary wavelet transformSecond-generation wavelet transformWavelet packet decompositionCascade algorithm

Citations

2,081

FWCI

21.65

field-weighted impact

References

Percentile

99%

vs. same field & year

Citations per year

Cited by

Modeling of solar energy systems using artificial neural network: A comprehensive review