Using separable functional network for function approximation

Author

Zhou, Yongquan ; Liu, Bai ; Huang, Huajuan ; Wei, Xingqong

Author_Institution

Coll. of Math. & Comput. Sci., Guangxi Univ. for Nat., Nanning

fYear

2008

fDate

26-28 Aug. 2008

Firstpage

855

Lastpage

858

Abstract

In this paper, separable functional network architecture and a learning algorithm of separable functional network are proposed, the learning of functional parameters use Lagrange multipliers by means of auxiliary function and solving a system of linear equations obtain parameters. An experiment in approximating typical continuous functions is given. The results show that the learning algorithm presented in the paper has excellent performance in approximation error.

Keywords

function approximation; learning (artificial intelligence); mathematics computing; multiplying circuits; Lagrange multiplier; auxiliary function; function approximation; learning algorithm; linear equation; separable functional network; Approximation algorithms; Computer architecture; Computer science; Educational institutions; Equations; Function approximation; Lagrangian functions; Mathematics; Network topology; Neurons; function approximation; functional network; functional parameters; learning algorithm; separable functional network;

fLanguage

English

Publisher

ieee

Conference_Titel

Granular Computing, 2008. GrC 2008. IEEE International Conference on

Conference_Location

Hangzhou

Print_ISBN

978-1-4244-2512-9

Electronic_ISBN

978-1-4244-2513-6

Type

conf

DOI

10.1109/GRC.2008.4664636

Filename

4664636