Title :
Recurrent NN model for chaotic time series prediction
Author :
Zhang, Jun ; Tang, K.S. ; Man, K.F.
Author_Institution :
Dept. of Electron. Eng., City Univ. of Hong Kong, Kowloon, Hong Kong
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 backpropagation 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 applications. Furthermore, this method is also very accurate in prediction as it can reach global minimum in a much attainable manner
Keywords :
chaos; learning (artificial intelligence); recurrent neural nets; time series; Elman neural network learning algorithm; chaotic time series prediction; global minimum; recurrent neural networks; time convergence; time data series; Artificial neural networks; Chaos; Computer networks; Convergence; Electronic mail; Feedforward systems; Neural networks; Predictive models; Recurrent neural networks; Time series analysis;
Conference_Titel :
Industrial Electronics, Control and Instrumentation, 1997. IECON 97. 23rd International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-7803-3932-0
DOI :
10.1109/IECON.1997.668440
