论文信息 - Approximation by radial bases and neural networks

Approximation by radial bases and neural networks

In this paper, we study approximation by radial basis functions including Gaussian, multiquadric, and thin plate spline functions, and derive order of approximation under certain conditions. Moreover, neural networks are also constructed by wavelet recovery formula and wavelet frames.

Xin Li | Charles A. Micchelli

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

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

[3] George A. Anastassiou. Rate of Convergence of Basic Multivariate Neural Network Operators to the Unit , 2000 .

[4] I. J. Schoenberg. Cardinal Spline Interpolation , 1987 .

[5] Charles A. Micchelli,et al. Multiquadric interpolation improved , 1992 .

[6] M. Buhmann. Multivariate cardinal interpolation with radial-basis functions , 1990 .

[7] Xin Li. Constructing near-tight wavelet frames by neural networks , 1996, Optics & Photonics.

[8] Xin Li,et al. On simultaneous approximations by radial basis function neural networks , 1998, Appl. Math. Comput..

[9] Christophe Rabut,et al. Elementarym-harmonic cardinal B-splines , 1992, Numerical Algorithms.

[10] George A. Anastassiou,et al. Rate of Convergence of Basic Neural Network Operators to the Unit-Univariate Case , 1997 .

[11] Allan Pinkus,et al. Approximation theory of the MLP model in neural networks , 1999, Acta Numerica.

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

[13] Charles A. Micchelli,et al. Interpolatory Subdivision Schemes and Wavelets , 1996 .

[14] Charles A. Micchelli. On a Family of Filters Arising in Wavelet Construction , 1997 .