On neural network training algorithm based on the unscented Kalman filter

Hongli Li, Jiang Wang, Yanqiu Che, Haiyang Wang, Yingyuan Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

Abstract

Neural network has been widely used for nonlinear mapping, time-series estimation and classification. The backprop-agation algorithm is a landmark of network weights training. Although the vast weights update algorithms have been developed, they are often plagued by convergence to poor local optima and low learn velocity. The unscented Kalman filter is a nonlinear parameter estimation algorithm. By means of it, weights update can be realized. Higher training velocity and mapping accuracy of network can be obtained. The numerical simulation results show the effectiveness of the algorithm compared with the standard backpropagation.

Original languageEnglish (US)
Title of host publicationProceedings of the 29th Chinese Control Conference, CCC'10
Pages1447-1450
Number of pages4
StatePublished - 2010
Event29th Chinese Control Conference, CCC'10 - Beijing, China
Duration: Jul 29 2010Jul 31 2010

Publication series

NameProceedings of the 29th Chinese Control Conference, CCC'10

Other

Other29th Chinese Control Conference, CCC'10
Country/TerritoryChina
CityBeijing
Period7/29/107/31/10

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'On neural network training algorithm based on the unscented Kalman filter'. Together they form a unique fingerprint.

Cite this