论文信息 - Note on error bounds for function approximation using nonlinear networks

Note on error bounds for function approximation using nonlinear networks

| For a variety of problems concerning classiication, compensation, adaptivity, identiication or signal processing, results concerning the representation and approximation of nonlinear functions can be of particular interest to engineers. Here we consider a large class of functions f that map I R n into the set of real or complex numbers, and we give bounds on the number of parameters needed so that f is approximated to within a prescribed degree of accuracy using a certain approximation network. Related work in the neural networks literature is also described .

Irwin W. Sandberg | Ajit Dingankar

[1] Chaouki T. Abdallah,et al. Error bounds in constructive approximation , 1996 .

[2] I. W. Sandberg. Approximations for nonlinear functionals , 1992 .

[3] C. Micchelli,et al. Approximation by superposition of sigmoidal and radial basis functions , 1992 .

[4] I. W. Sandberg. Approximations for nonlinear functions , 1992 .

[5] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

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

[7] Andrew R. Barron,et al. Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[8] Irwin W. Sandberg,et al. A note on error bounds for approximation in inner product spaces , 1996 .

[9] L. Jones. A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training , 1992 .