An efficient neural network for solving convex optimization problems with a nonlinear complementarity problem function
- 19 Downloads
In this paper, we present a one-layer recurrent neural network (NN) for solving convex optimization problems by using the Mangasarian and Solodov (MS) implicit Lagrangian function. In this paper by using Krush–Kuhn–Tucker conditions and MS function the NN model was derived from an unconstrained minimization problem. The proposed NN model is one layer and compared to the available NNs for solving convex optimization problems, which has a better performance in convergence time. The proposed NN model is stable in the sense of Lyapunov and globally convergent to optimal solution of the original problem. Finally, simulation results on several numerical examples are presented and the validity of the proposed NN model is demonstrated.
KeywordsOne-layer neural networks Convex programming Nonlinear complementarity problem
Compliance with ethical standards
Conflict of interest
All authors have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Bouzerdoum A, Pattison TR (1993) Neural network for quadratic optimization with bound constraints. IEEE Trans Neural Netw 4(2):293–304Google Scholar
- Effati S, Mansoori A, Eshaghnezhad M (2015) An efficient projection neural network for solving bilinear programming problems. Neurocomputing 168:1188–1197Google Scholar
- Ferris MC, Kanzow C (2002) Complementarity and related problems: a survey. In: Handbook of applied optimization. Oxford University Press, New York, pp 514–530 Google Scholar
- Ferris MC, Mangasarian OL, Pang JS (eds) (2001) Complementarity: applications, algorithms and extensions. Kluwer Academic Publishers, DordrechtGoogle Scholar
- Huang X, Cui B (2016) A novel neural network for solving convex quadratic programming problems subject to equality and inequality constraints. Neurocomputing 214:23–31Google Scholar
- Nazemi AR (2013) Solving general convex nonlinear optimization problems by an efficient neurodynamic model. Eng Appl Artif Intell 26(2):685–696Google Scholar
- Nazemi AR (2014) A neural network model for solving convex quadratic programming problems with some applications. Eng Appl Artif Intell 32:54–62Google Scholar
- Ranjbar M, Effati S, Miri SM (2017) An artificial neural network for solving quadratic zero-one programming problems. Neurocomputing 235:192–198Google Scholar
- Slotin JJE, Li W (1991) Applied nonlinear control. Prentice Hall, Upper Saddle RiverGoogle Scholar
- Tank DW, Hopfield JJ (1986) Simple neural optimization networks: an A/D converter, signal decision network and a linear programming circuit. IEEE Trans Circuits Syst 33:533–541Google Scholar
- Xia Y (1996) A new neural network for solving linear programming problems and its application. IEEE Trans Neural Netw 7:525–529Google Scholar
- Xia Y, Wang J (2000) A recurrent neural network for solving linear projection equations. Neural Netw 13:337–350Google Scholar
- Xia Y, Wang J (2005) A recurrent neural network for solving nonlinear convex programs subject to linear constraints. IEEE Trans Neural Netw 16(2):1045–1053Google Scholar