Wavelet networks as an alternative to neural networks

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.

[1]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[2]  Dirk Thierens,et al.  Non-redundant genetic coding of neural networks , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[3]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[4]  Yoshifusa Ito,et al.  Approximation Capability of Layered Neural Networks with Sigmoid Units on Two Layers , 1994, Neural Computation.

[5]  Vera Kurková,et al.  Kolmogorov's theorem and multilayer neural networks , 1992, Neural Networks.

[6]  Kurt Hornik,et al.  Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[7]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[8]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[9]  David B. Fogel,et al.  An introduction to simulated evolutionary optimization , 1994, IEEE Trans. Neural Networks.

[10]  Pierre Cardaliaguet,et al.  Approximation of a function and its derivative with a neural network , 1992, Neural Networks.

[11]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[12]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[13]  Cheng-Yan Kao,et al.  A combined evolutionary algorithm for real parameters optimization , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[14]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[15]  Kurt Hornik,et al.  FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .

[16]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.