Recurrent NN model for chaotic time series prediction
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Pages (from-to) | 1108-1112 |
| Journal / Publication | IECON Proceedings (Industrial Electronics Conference) |
| Volume | 3 |
| Publication status | Published - 1997 |
Conference
| Title | Proceedings of the 1997 23rd Annual International Conference on Industrial Electronics, Control, and Instrumentation, IECON. Part 2 (of 4) |
|---|---|
| City | New Orleans, LA, USA |
| Period | 9 - 14 November 1997 |
Link(s)
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.
Citation Format(s)
Recurrent NN model for chaotic time series prediction. / Zhang, Jun; Tang, K. S.; Man, K. F.
In: IECON Proceedings (Industrial Electronics Conference), Vol. 3, 1997, p. 1108-1112.
In: IECON Proceedings (Industrial Electronics Conference), Vol. 3, 1997, p. 1108-1112.
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
