Title :
Radial basis function networks and complexity regularization in function learning and classification
Author :
Kégl, Balázs ; Krzyak, A. ; Niemann, Heinrich
Author_Institution :
Dept. of Math. & Stat., Queen´´s Univ., Kingston, Ont., Canada
Abstract :
We apply complexity regularization to learn normalized radial basis function networks in nonparametric classification. We study convergence and the rates of convergence of the empirically trained networks and verify the results in computer experiments
Keywords :
convergence; covariance matrices; learning (artificial intelligence); nonparametric statistics; pattern classification; radial basis function networks; complexity regularization; empirically trained networks; function learning; nonparametric classification; Approximation error; Computer networks; Convergence; Estimation error; Intelligent networks; Mathematics; Neurons; Radial basis function networks; Statistics; Vectors;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.906022
