Convergence of Online Gradient Algorithm with Stochastic Inputs for Pi-Sigma Neural Networks

Author

Kang, Xidai ; Xiong, Yan ; Zhang, Chao ; Wu, Wei

Author_Institution

Dept. of Appl. Math., Dalian Univ. of Technol.

fYear

2007

fDate

1-5 April 2007

Firstpage

564

Lastpage

569

Abstract

An online gradient method is presented and discussed for Pi-Sigma neural networks with stochastic inputs. The error function is proved to be monotone in the training process, and the gradient of the error function tends to zero if the weights sequence is uniformly bounded. Furthermore, after adding a moderate condition, the weights sequence itself is also proved to be convergent

Keywords

convergence; feedforward neural nets; gradient methods; stochastic processes; Pi-Sigma neural networks; convergence; error function; online gradient algorithm; stochastic inputs; weights sequence; Chaos; Computational efficiency; Computational intelligence; Convergence; Feedforward neural networks; Gradient methods; Mathematics; Neural networks; Polynomials; Stochastic processes; Pi-Sigma neural network; convergence; monotonicity; online gradient algorithm; stochastic input;

fLanguage

English

Publisher

ieee

Conference_Titel

Foundations of Computational Intelligence, 2007. FOCI 2007. IEEE Symposium on

Conference_Location

Honolulu, HI

Print_ISBN

1-4244-0703-6

Type

conf

DOI

10.1109/FOCI.2007.371528

Filename

4233962

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2821760