DocumentCode :
2400014
Title :
Uniform approximation and the complexity of neural networks
Author :
Ferreira, Paulo J S G ; Cao, Si-Qi
Author_Institution :
Dept. de Electron. e Telecoms, Aveiro Univ., Portugal
fYear :
1997
fDate :
24-26 Sep 1997
Firstpage :
141
Lastpage :
148
Abstract :
Studies some of the approximating properties of feedforward neural networks as a function of the number of nodes. Two cases are considered: sigmoidal and radial basis function networks. Bounds for the approximation error are given. The methods through which we arrive at the bounds are constructive. The error studied is the L or sup error
Keywords :
computational complexity; feedforward neural nets; function approximation; L error; approximating properties; approximation error; complexity; feedforward neural networks; radial basis function networks; sigmoidal networks; sup error; uniform approximation; Approximation error; Computer networks; Electronic mail; Feedforward neural networks; Feedforward systems; Neural networks; Radial basis function networks; Radiofrequency interference;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks for Signal Processing [1997] VII. Proceedings of the 1997 IEEE Workshop
Conference_Location :
Amelia Island, FL
ISSN :
1089-3555
Print_ISBN :
0-7803-4256-9
Type :
conf
DOI :
10.1109/NNSP.1997.622392
Filename :
622392
Link To Document :
بازگشت