Title :
Rational functional network for function approximation
Author :
Zhou, Yongquan ; Liu, Bai ; Xie, Zhucheng ; Luo, Dexiang
Author_Institution :
Coll. of Math. & Comput. Sci., Guangxi Univ. for Nat., Nanning, China
Abstract :
This paper presents a new functional network which is based on rational function. A learning algorithm of rational functional network is proposed, the learning of functional network parameters use Lagrange multipliers by means of auxiliary function and solving a system of linear equations obtain parameters. An experiment in approximating rational functions is given. The results show that the rational functional function has excellent performance in approximation error.
Keywords :
function approximation; learning (artificial intelligence); neural nets; rational functions; Lagrange multipliers; approximation error; function approximation; learning algorithm; linear equations; rational functional network; Educational institutions; Equations; Function approximation; Intelligent networks; Intelligent systems; Knowledge engineering; Mathematics; Neural networks; Neurons; Predictive models;
Conference_Titel :
Intelligent System and Knowledge Engineering, 2008. ISKE 2008. 3rd International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-2196-1
Electronic_ISBN :
978-1-4244-2197-8
DOI :
10.1109/ISKE.2008.4731044
