Zhang, Faming; Zhang, Changfan; Yu, Huijun Exponential stability of quadratic optimization on neural networks. (Chinese. English summary) Zbl 1187.90215 J. Huazhong Univ. Sci. Technol. 36, No. 5, 57-59 (2008). 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. Cited in 1 Document 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 Keywords:cellular neural networks; global exponential stability; quadratic optimization; matrix eigenvalue; neural network model; exponential convergence rate PDFBibTeX XMLCite \textit{F. Zhang} et al., J. Huazhong Univ. Sci. Technol. 36, No. 5, 57--59 (2008; Zbl 1187.90215)