Quasi-Lagrangian Neural Network for Convex Quadratic Optimization

  title={Quasi-Lagrangian Neural Network for Convex Quadratic Optimization},
  author={Giovanni Costantini and Renzo Perfetti and Massimiliano Todisco},
  journal={IEEE Transactions on Neural Networks},
A new neural network for convex quadratic optimization is presented in this brief. The proposed network can handle both equality and inequality constraints, as well as bound constraints on the optimization variables. It is based on the Lagrangian approach, but exploits a partial dual method in order to keep the number of variables at minimum. The dynamic evolution is globally convergent and the steady-state solutions satisfy the necessary and sufficient conditions of optimality. The circuit… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 14 references

Nonlinear Programming: Theory and Algorithms, ser. Wiley-Interscience Series in Discrete Mathematics and Optimization

  • M. Bazaraa, D. Sherali, C. Shetty
  • New York: Wiley,
  • 1992
1 Excerpt

Neural networks for nonlinear programming

  • M. P. Kennedy, L. O. Chua
  • IEEE Trans. Circuits Syst., vol. CAS-35, no. 5…
  • 1988
3 Excerpts

Quadratic programming analogs

  • G. Wilson
  • IEEE Trans. Circuits Syst., vol. CAS-33, no. 9…
  • 1986
1 Excerpt

Similar Papers

Loading similar papers…