Multiperiodicity and Attractivity Analysis for Discrete-Time Second Order Delayed Recurrent Neural Networks

作者：Qiu Fang^*

来源：Arabian Journal for Science and Engineering, 2013, 38(5): 1269-1280.

DOI：10.1007/s13369-013-0603-4

• Second order recurrent neural network
• Discrete-time
• Multiperiodicity
• Attractivity
• Periodic orbit

This paper investigates the multiperiodicity and attractivity of discrete-time second order recurrent neural networks. Sufficient conditions are obtained for the existence of 2(n) locally attractive periodic orbits in an n-dimensional network. Also, the state space is divided into 3(n) regions and sufficient conditions are given to ensure that a periodic orbit belonging to one of these regions is locally or globally attractive. As particular cases, cellular neural networks and Hopfield neural networks are also investigated. Some numerical simulations are given which remarkably demonstrate the theoretical results.

• 出版日期2013-5
• 单位滨州学院