Recurrent NN model for chaotic time series prediction

Jun Zhang; K. S. Tang; K. F. Man

doi:10.1109/IECON.1997.668440

Recurrent NN model for chaotic time series prediction

Jun Zhang
, K. S. Tang
, K. F. Man

City University of Hong Kong

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

13 Citations (Scopus)

Abstract

A new Elman neural network learning algorithm is proposed for chaotic time series prediction. This method has a number of advantages over the use of a standard Back-Propagation (BP) algorithm. It is not only its capability for handling a much higher complexity time data series, but its superiority in time convergence can prove to be a valuable asset for time critical application. Furthermore, this method is also very accurate in prediction as it can reach global minimum in a much attainable manner.

Original language	English
Pages (from-to)	1108-1112
Journal	IECON Proceedings (Industrial Electronics Conference)
Volume	3
DOIs	https://doi.org/10.1109/IECON.1997.668440
Publication status	Published - 1997
Event	23rd Annual International Conference on Industrial Electronics, Control, and Instrumentation (IECON '97) - New Orleans, LA, United States Duration: 9 Nov 1997 → 14 Nov 1997

Access Output

10.1109/IECON.1997.668440

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{f9b79cd3cfb14b7981a6502f99d5cdbb,

title = "Recurrent NN model for chaotic time series prediction",

abstract = "A new Elman neural network learning algorithm is proposed for chaotic time series prediction. This method has a number of advantages over the use of a standard Back-Propagation (BP) algorithm. It is not only its capability for handling a much higher complexity time data series, but its superiority in time convergence can prove to be a valuable asset for time critical application. Furthermore, this method is also very accurate in prediction as it can reach global minimum in a much attainable manner.",

author = "Jun Zhang and Tang, \{K. S.\} and Man, \{K. F.\}",

year = "1997",

doi = "10.1109/IECON.1997.668440",

language = "English",

volume = "3",

pages = "1108--1112",

journal = "IECON Proceedings (Industrial Electronics Conference)",

note = "23rd Annual International Conference on Industrial Electronics, Control, and Instrumentation (IECON '97) ; Conference date: 09-11-1997 Through 14-11-1997",

}

TY - JOUR

T1 - Recurrent NN model for chaotic time series prediction

AU - Zhang, Jun

AU - Tang, K. S.

AU - Man, K. F.

PY - 1997

Y1 - 1997

N2 - A new Elman neural network learning algorithm is proposed for chaotic time series prediction. This method has a number of advantages over the use of a standard Back-Propagation (BP) algorithm. It is not only its capability for handling a much higher complexity time data series, but its superiority in time convergence can prove to be a valuable asset for time critical application. Furthermore, this method is also very accurate in prediction as it can reach global minimum in a much attainable manner.

AB - A new Elman neural network learning algorithm is proposed for chaotic time series prediction. This method has a number of advantages over the use of a standard Back-Propagation (BP) algorithm. It is not only its capability for handling a much higher complexity time data series, but its superiority in time convergence can prove to be a valuable asset for time critical application. Furthermore, this method is also very accurate in prediction as it can reach global minimum in a much attainable manner.

UR - https://www.scopus.com/pages/publications/0031367676

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0031367676&origin=recordpage

U2 - 10.1109/IECON.1997.668440

DO - 10.1109/IECON.1997.668440

M3 - RGC 21 - Publication in refereed journal

VL - 3

SP - 1108

EP - 1112

JO - IECON Proceedings (Industrial Electronics Conference)

JF - IECON Proceedings (Industrial Electronics Conference)

T2 - 23rd Annual International Conference on Industrial Electronics, Control, and Instrumentation (IECON '97)

Y2 - 9 November 1997 through 14 November 1997

ER -

Recurrent NN model for chaotic time series prediction

Abstract

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this