Subgradient-based feedback neural networks for non-differentiable convex optimization problems

  • Li Guocheng 
  • Song Shiji Email author
  • Wu Cheng 


This paper developed the dynamic feedback neural network model to solve the convex nonlinear programming problem proposed by Leung et al. and introduced subgradient-based dynamic feedback neural networks to solve non-differentiable convex optimization problems. For unconstrained non-differentiable convex optimization problem, on the assumption that the objective function is convex coercive, we proved that with arbitrarily given initial value, the trajectory of the feedback neural network constructed by a projection subgradient converges to an asymptotically stable equilibrium point which is also an optimal solution of the primal unconstrained problem. For constrained non-differentiable convex optimization problem, on the assumption that the objective function is convex coercive and the constraint functions are convex also, the energy functions sequence and corresponding dynamic feedback subneural network models based on a projection subgradient are successively constructed respectively, the convergence theorem is then obtained and the stopping condition is given. Furthermore, the effective algorithms are designed and some simulation experiments are illustrated.


projection subgradient non-differentiable convex optimization convergence feedback neural network 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hopfield J J, Tank D W. Neural computation of decisions in optimization problems. Biol Cybern, 1985, 52: 141–152zbMATHMathSciNetGoogle Scholar
  2. 2.
    Tank D W, Hopfield J J. Simple neural optimization network: An A/D converter, signal decision circuit, and a linear programming circuit. IEEE Trans Circuits Syst, 1986, 33: 533–541CrossRefGoogle Scholar
  3. 3.
    Kennedy M P, Chua L O. Neural networks for nonlinear programming. IEEE Trans Circuits Syst, 1988, 35: 554–562MathSciNetCrossRefGoogle Scholar
  4. 4.
    Rodríguez-Vázquez A, Rueda R, Huertas J L, et al. Nonlinear switched-capacitor neural networks for optimization problems. IEEE Trans Circuits Syst, 1990, 37: 384–397CrossRefGoogle Scholar
  5. 5.
    Bouzerdoum A, Pattison T R. Neural network for quadratic optimization with bound constraints. IEEE Trans Neural Networks, 1993, 4: 293–304CrossRefGoogle Scholar
  6. 6.
    Sudharsanan S, Sundareshan M. Exponential stability and a systematic synthesis of a neural network for quadratic minimization. Neural Networks, 1991, 4: 599–613CrossRefGoogle Scholar
  7. 7.
    Leung Y, Chen K Z, Gao X B. A high-performance feedback neural network for solving convex nonlinear programming problems. IEEE Trans Neural Networks, 2003, 14: 1469–1477CrossRefGoogle Scholar
  8. 8.
    Aubin J P, Cellina A. Differential Inclusions. Berlin: Springer-Verlag, 1984Google Scholar
  9. 9.
    Ortega J M, Rheinboldt W C. Iterative Solution of Nonlinear Equation in Several Variables. New York: Academic, 1970Google Scholar
  10. 10.
    Dimitri P B. Nonlinear Programming. 2nd ed. Belmont: Athena Scientific, 1999Google Scholar
  11. 11.
    Filippov A F. Differential Equations with Discontinuous Righthand Sides. Dordrecht: Kluwer Academic, 1988Google Scholar

Copyright information

© Science in China Press 2006

Authors and Affiliations

  1. 1.Center of Intelligent and Networked Systems, Department of AutomationTsinghua UniversityBeijingChina

Personalised recommendations