DocumentCode
341410
Title
A new hybrid recurrent neural network
Author
Lu, Xiqun ; Chen, Chun
Author_Institution
Dept. of Comput. Sci. & Eng., Univ. of Zhe Jiang, Hang Zhou, China
Volume
5
fYear
1999
fDate
1999
Firstpage
616
Abstract
A new hybrid type of recurrent neural network is reported in this paper. Unlike those of the general recurrent neural networks, the activation functions of its hidden neurons are chosen to be Gaussian functions. The performance of this hybrid network for nonlinear nonstationary time series prediction is tested. Two popular time series produced by the Mackey-Glass equation and the Lorenz equation are used in the simulation
Keywords
Gaussian distribution; recurrent neural nets; time series; Gaussian functions; Lorenz equation; Mackey-Glass equation; activation functions; hybrid recurrent neural network; nonlinear nonstationary time series prediction; time series; Computer science; Multi-layer neural network; Neural networks; Neurofeedback; Neurons; Nonlinear equations; Predictive models; Recurrent neural networks; Statistical analysis; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on
Conference_Location
Orlando, FL
Print_ISBN
0-7803-5471-0
Type
conf
DOI
10.1109/ISCAS.1999.777647
Filename
777647
Link To Document