论文信息 - The Circuit Implementation of a Wavelet Function Approximator

The Circuit Implementation of a Wavelet Function Approximator

This paper describes the analog synthesis of a wavelet function approximator using sigmoidal mother wavelet. Any finite energy multivariate function can be approximated by this analog circuit using the multiresolution approximation property of the wavelet decomposition. The approximator circuit includes bipolar junction transistors, operational amplifiers and linear passive circuit elements.

F. Acar Savaci | Mustafa Gündüzalp | Nalan Ozkurt

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

[2] Ingrid Daubechies,et al. Ten Lectures on Wavelets , 1992 .

[3] David Allingham,et al. Wavelet reconstruction of nonlinear dynamics , 1998 .

[4] Massimo Conti,et al. Approximate identity neural networks for analog synthesis of nonlinear dynamical systems , 1994 .

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

[6] Y. Meyer. Wavelets and Operators , 1993 .

[7] Yagyensh C. Pati,et al. Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations , 1993, IEEE Trans. Neural Networks.

[8] Liangyue Cao,et al. Predicting chaotic time series with wavelet networks , 1995 .

[9] Qinghua Zhang,et al. Using wavelet network in nonparametric estimation , 1997, IEEE Trans. Neural Networks.

[10] Carver Mead,et al. Analog VLSI and neural systems , 1989 .

[11] F. Girosi,et al. Networks for approximation and learning , 1990, Proc. IEEE.