Title :
Asymptotic approximation power for neural networks
Author :
Ferreira, Paulo J S G ; Pinho, Armando J.
Author_Institution :
Univ. of Aveiro, Portugal
Abstract :
This paper studies the asymptotic approximation power of radial basis function neural networks in the sup norm. The methods used are constructive and based on discretization of approximate identities. The effect of the kernel on the approximation order is discussed
Keywords :
computational complexity; convergence of numerical methods; feedforward neural nets; function approximation; approximation order; asymptotic approximation power; computational complexity; convergence; discretization; function approximation; radial basis function neural networks; Approximation error; Approximation methods; Convergence; Fourier series; Interpolation; Joining processes; Kernel; Neural networks; Nonlinear filters; Radial basis function networks;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.685955
