Existence and global exponential stability of periodic solution for high-order discrete-time BAM neural networks

• Published in: Neural Networks Vol. 50; pp. 98 - 109
• Main Authors: Zhang, Ancai, Qiu, Jianlong, She, Jinhua
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.02.2014; Elsevier BV; Elsevier
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Association Learning; Association Learning - physiology; Bidirectional associative memory (BAM); Computer science; control theory; systems; Computer Simulation; Connectionism. Neural networks; Discrete-time; Exact sciences and technology; Exponential stability; High-order neural networks; Humans; Memory; Memory - physiology; Neural Networks, Computer; Time Factors; Young’s inequality; High-order neural networks; Bidirectional associative memory (BAM); Discrete-time; Exponential stability; Young’s inequality; Existence of solution; Lyapunov method; Neural network; Periodic solution; Degree theory; Modeling; Young's inequality; Bidirectional associative memory; Associative memory; Time varying system; Discrete time; Delay time; Heteroassociation
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2013.11.005

This paper concerns the existence and exponential stability of periodic solution for the high-order discrete-time bidirectional associative memory (BAM) neural networks with time-varying delays. First, we present the criteria for the existence of periodic solution based on the continuation theorem of coincidence degree theory and the Young’s inequality, and then we give the criteria for the global exponential stability of periodic solution by using a non-Lyapunov method. After that, we give a numerical example that demonstrates the effectiveness of the theoretical results. The criteria presented in this paper are easy to verify. In addition, the proposed analysis method is easy to extend to other high-order neural networks.