Risk Sensitive Optimal Synchronization of Coupled Stochastic Neural Networks with Chaotic Phenomena
MetadataShow full item record
SubjectDecision support systems; Synchronization; Neural networks; State feedback; Noise; Sensitivity; Optimal control
This paper presents a new theoretical design of how an optimal synchronization is achieved for stochastic coupled neural networks with respect to a risk sensitive optimality criterion. The approach is rigorously developed by using the Hamilton-Jacobi-Bellman equation, Lyapunov technique, and inverse optimality, to obtain a risk sensitive state feedback controller, which guarantees that the chaotic drive network synchronizes with the chaotic response network influenced by uncertain noise signals, with an eye on a given risk sensitivity parameter. Finally, a numerical example is given to demonstrate the effectiveness of the proposed approach.
This article was published in the 2015 IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA). Date of conference: 26-28 May 2015. DOI: 10.1109/CISDA.2015.7208632. Copyright IEEE 2015.