×

Exponential stability of quadratic optimization on neural networks. (Chinese. English summary) Zbl 1187.90215

Summary: In view of convex quadratic optimization with boundary constrains, a cellular neural network is established by using the principle of the mathematical model of discrete-time neural networks model. Based on the relationship between matrix and symmetric matrix global exponential stability of the discrete-time neural networks model and the an exponential convergence rate are obtained by using the characteristics of eigenvalues of a positive definite matrix and introducing a proper factor. The paper also studies the advantages and disadvantages of the result and puts forward three ways to solve the problems. The paper illustrates the applicability of the result with an example.

MSC:

90C20 Quadratic programming
90C25 Convex programming
68T05 Learning and adaptive systems in artificial intelligence
92B20 Neural networks for/in biological studies, artificial life and related topics
PDFBibTeX XMLCite