A projection neural network and its application to constrained optimization problems
Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal
Author(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 447-458 |
Journal / Publication | IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications |
Volume | 49 |
Issue number | 4 |
Publication status | Published - Apr 2002 |
Externally published | Yes |
Link(s)
Abstract
In this paper, we present a recurrent neural network for solving the nonlinear projection formulation. It is shown here that the proposed neural network is stable in the sense of Lyapunov and globally convergent, globally asymptotically stable, and globally exponentially stable, respectively under different conditions. Compared with the existing neural network for solving the projection formulation, the proposed neural network has a single-layer structure and is amenable to parallel implementation. Moreover, the proposed neural network has no Lipschitz condition, and, thus can be applied to solve a very broad class of constrained optimization problems that are special cases of the nonlinear projection formulation. Simulation shows that the proposed neural network is effective in solving these constrained optimization problems.
Research Area(s)
- Constrained optimization problems, Global stability, Recurrent neural network
Citation Format(s)
A projection neural network and its application to constrained optimization problems. / Xia, Youshen; Leung, Henry; Wang, Jun.
In: IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, Vol. 49, No. 4, 04.2002, p. 447-458.
In: IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, Vol. 49, No. 4, 04.2002, p. 447-458.
Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal