Bf. Liu et J. Si, THE BEST APPROXIMATION TO C-2 FUNCTIONS AND ITS ERROR-BOUNDS USING REGULAR-CENTER GUASSIAN NETWORKS, IEEE transactions on neural networks, 5(5), 1994, pp. 845-847
Gaussian neural networks are considered to approximate any C2 function
with support on the unit hypercube I(m) = [0, 1]m in the sense of bes
t approximation. An upper bound (O(N-2)) of the approximation error is
obtained in the present letter for a Gaussian network having N(m) hid
den neurons with centers defined on a regular mesh in I(m).