Title :
Feasibility of random basis function approximators for modeling and control
Author :
Tyukin, Ivan Yu ; Prokhorov, Danil V.
Author_Institution :
Dept. of Math., Univ. of Leicester, Leicester, UK
Abstract :
We discuss the role of random basis function approximators in modeling and control. We analyze the published work on random basis function approximators and demonstrate that their favorable error rate of convergence O(1/n) is guaranteed only with very substantial computational resources. We also discuss implications of our analysis for applications of neural networks in modeling and control.
Keywords :
computational complexity; convergence of numerical methods; function approximation; large-scale systems; computational resources; convergence; favorable error rate; neural network; random basis function approximator; Approximation error; Control system synthesis; Convergence; Error analysis; Gaussian processes; Intelligent control; Intelligent systems; Mathematical model; Neural networks; Radial basis function networks;
Conference_Titel :
Control Applications, (CCA) & Intelligent Control, (ISIC), 2009 IEEE
Conference_Location :
St. Petersburg
Print_ISBN :
978-1-4244-4601-8
Electronic_ISBN :
978-1-4244-4602-5
DOI :
10.1109/CCA.2009.5281061
