
	Journal of Artificial Intelligence
	Year: 2014 \| Volume: 7 \| Issue: 1 \| Page No.: 24-34 DOI: 10.3923/jai.2014.24.34

Discrete Time Dynamic Neural Networks for Predicting Chaotic Time Series

Forough Marzban, Ramin Ayanzadeh and Pouria Marzban

Abstract: Today chaotic dynamical behavior in scientific field is focused by the researchers. There have been many studies on chaotic systems. In addition, scientists achieved that chaotic dynamical behaviors play an important role in biological neural networks. Therefore, they are trying to model natural neuron's behavior with artificial neuron by using chaotic dynamic. It’s obvious that, chaos theory describes the behavior of certain dynamical systems which evolve with time that may exhibit dynamics that are highly sensitive to initial conditions and depend on its dynamic properties. Designing such a system which has enough ability, for identification and predication is our final goals. In chaotic system, the initial conditions are changed in each steps and there isn’t a clear dynamic system. This study reviews the fundamentals of chaos theory, its application and tries to identify and predicate them by using dynamic neural network which has more adaption with different types of condition. In this study, first of all some definition of chaos is explained, then the two different types of dynamic neural units are introduced, next by using these structures, some chaotic systems such as Henon map and Mackey-glass series are identified and predicted.

PDF Fulltext XML References Citation Report Citation

RELATED ARTICLES:

•	Fuzzy Cellular Automata Based Random Numbers Generation

•	Honey Bees Foraging Optimization for Mixed Nash Equilibrium Estimation

•	Determining Optimum Queue Length in Computer Networks by Using Memetic Algorithms

•	Innovative Approach to Generate Uniform Random Numbers Based on a Novel Cellular Automata

How to cite this article:

Forough Marzban, Ramin Ayanzadeh and Pouria Marzban, 2014. Discrete Time Dynamic Neural Networks for Predicting Chaotic Time Series. Journal of Artificial Intelligence, 7: 24-34.

DOI: 10.3923/jai.2014.24.34

URL: https://scialert.net/abstract/?doi=jai.2014.24.34

COMMENT ON THIS PAPER

Navigation


		Online First
		Current Issue
		Previous Issues
		Editorial Board
		Submit a Manuscript
		Guide to Authors
		Subscribe to E-alerts

Indexed In


		ASCI-Database
		Asian Digital Library
		Google Scholar
		SCIMAGO

Science Alert