论文信息 - Splines, Rational Functions and Neural Networks

Splines, Rational Functions and Neural Networks

Connections between spline approximation, approximation with rational functions, and feedforward neural networks are studied. The potential improvement in the degree of approximation in going from single to two hidden layer networks is examined. Some results of Birman and Solomjak regarding the degree of approximation achievable when knot positions are chosen on the basis of the probability distribution of examples rather than the function values are extended.

Peter L. Bartlett | Robert C. Williamson | R. C. Williamson | P. Bartlett

[1] Andrew Donald Booth,et al. Theory of the transmission and processing of information , 1961 .

[2] M. Birman,et al. PIECEWISE-POLYNOMIAL APPROXIMATIONS OF FUNCTIONS OF THE CLASSES $ W_{p}^{\alpha}$ , 1967 .

[3] H. Ekblom. Lp-methods for robust regression , 1974 .

[4] H. Triebel. Theory Of Function Spaces , 1983 .

[5] P. Petrushev. Direct and converse theorems for spline and rational approximation and besov spaces , 1988 .

[6] P. Petrushev,et al. Rational Approximation of Real Functions , 1988 .

[7] Leon O. Chua,et al. Canonical piecewise-linear representation , 1988 .

[8] P. Oswald. On the degree of nonlinear spline approximation in Besov-Sobolev spaces , 1990 .

[9] R. DeVore,et al. Compression of wavelet decompositions , 1992 .

[10] David Haussler,et al. Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications , 1992, Inf. Comput..