Title :
Variable Weighted Learning Algorithm and Its Convergence Rate
Author :
Fangyuan Yu ; Zhenfa Hu
Author_Institution :
Sch. of Sci., Hubei Automotive Ind. Inst., Shiyan, China
Abstract :
Variable weighted learning Algorithm based on empirical data is introduced and the classical principle empirical risk minimization becomes its special case.The estimates of the convergence rate are given via integral operators and their approximations.
Keywords :
convergence; integral equations; learning (artificial intelligence); minimisation; convergence rate; empirical risk minimization; integral operators; variable weighted learning; Automotive engineering; Biological system modeling; Computer industry; Convergence; Extraterrestrial measurements; Hilbert space; Kernel; Machine learning; Probability distribution; Risk management; Empirical risk minimization; Variable weighted learning algorithm; integral operators;
Conference_Titel :
Natural Computation, 2009. ICNC '09. Fifth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3736-8
DOI :
10.1109/ICNC.2009.397
