Title :
Nonparametric classification using radial basis function nets and empirical risk minimization
Author :
Krzyzak, Adam ; Linder, Tamas ; Lugosi, Gabor
Author_Institution :
Dept. of Comput. Sci., Concordia Univ., Montreal, Que., Canada
Abstract :
We study convergence properties of radial basis function (RBF) networks in nonparametric classification for a large class of basis functions with parameters of RBF nets learned through empirical risk minimization. In the classification (pattern recognition) problem, based upon the observation of a random vector X∈Rd, one has to guess the value of a corresponding label Y, where Y is a random variable taking its values from (-1,1)
Keywords :
convergence of numerical methods; feedforward neural nets; learning (artificial intelligence); minimisation; pattern recognition; basis functions; convergence properties; empirical risk minimization; nonparametric classification; pattern recognition; radial basis function nets; radial basis function networks; random variable; random vector; Approximation error; Convergence; Error probability; Kernel; Pattern recognition; Q measurement; Radial basis function networks; Random variables; Risk management; Virtual colonoscopy;
Conference_Titel :
Information Theory, 1995. Proceedings., 1995 IEEE International Symposium on
Conference_Location :
Whistler, BC
Print_ISBN :
0-7803-2453-6
DOI :
10.1109/ISIT.1995.535773
