Title :
The best approximation to C2 functions and its error bounds using regular-center Gaussian networks
Author :
Liu, Binfan ; Si, Jennie
Author_Institution :
Dept. of Electr. Eng., Arizona State Univ., Tempe, AZ, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
Gaussian neural networks are considered to approximate any C2 function with support on the unit hypercube Im=[0,1] m in the sense of best approximation. An upper bound (0(N-2)) of the approximation error is obtained in the present paper for a Gaussian network having Nm hidden neurons with centers defined on a regular mesh in Im
Keywords :
approximation theory; feedforward neural nets; function approximation; optimisation; C2 functions; Gaussian neural networks; approximation; error bounds; hidden neurons; hypercube; radial basis network; upper bound; Approximation error; Artificial neural networks; Fourier transforms; Hypercubes; Interpolation; Neural networks; Neurons; Nonhomogeneous media; Polynomials; Upper bound;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374595
