Differential Inclusions-Based Neural Networks for Nonsmooth Convex Optimization on a Closed Convex Subset
Differential inclusions-based dynamic feedback neural network models are introduced to solve in real time nonsmooth convex optimization problems restricted on a closed convex subset of R n . First,a differential inclusion-based dynamic feedback neural network model for solving unconstrained optimization problem is established, and its stability and convergence are investigated, then based on the preceding results and the method of successive approximation, differential inclusions-based dynamic feedback neural network models for solving in real time nonsmooth optimization problem on a closed convex subset are successively constructed, and its dynamical behavior and optimization capabilities are analyzed rigorously.
Unable to display preview. Download preview PDF.
- 13.Filippov, A.F.: Differential Equations with Discontinuous Righthand Sides. Kluwer Academic, Dordrecht (1988)Google Scholar
- 14.Li, G., Song, S., Wu, C.: Subgradient-Based Feedback Neural Networks for Nondifferentiable Convex Optimization Problems. Science in China, Series F 49, 91–106 (2006)Google Scholar