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 :
9/1/1994 12:00:00 AM
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 (O(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 :
error analysis; feedforward neural nets; function approximation; C2 functions; Gaussian neural networks; approximation error; best approximation; error bounds; hidden neurons; regular mesh; regular-center Gaussian networks; unit hypercube; upper bound; Approximation error; Approximation methods; Fourier transforms; Hypercubes; Joining processes;
Journal_Title :
Neural Networks, IEEE Transactions on