Generalized neural network for nonsmooth nonlinear programming problems

In 1988 Kennedy and Chua introduced the dynamical canonical nonlinear programming circuit (NPC) to solve in real time nonlinear programming problems where the objective function and the constraints are smooth (twice continuously differentiable) functions. In this paper, a generalized circuit is introduced (G-NPC), which is aimed at solving in real time a much wider class of nonsmooth nonlinear programming problems where the objective function and the constraints are assumed to satisfy only the weak condition of being regular functions. G-NPC, which derives from a natural extension of NPC, has a neural-like architecture and also features the presence of constraint neurons modeled by ideal diodes with infinite slope in the conducting region. By using the Clarke's generalized gradient of the involved functions, G-NPC is shown to obey a gradient system of differential inclusions, and its dynamical behavior and optimization capabilities, both for convex and nonconvex problems, are rigorously analyzed in the framework of nonsmooth analysis and the theory of differential inclusions. In the special important case of linear and quadratic programming problems, salient dynamical features of G-NPC, namely the presence of sliding modes , trajectory convergence in finite time, and the ability to compute the exact optimal solution of the problem being modeled, are uncovered and explained in the developed analytical framework.

[1]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[2]  Leon O. Chua,et al.  Neural networks for nonlinear programming , 1988 .

[3]  Aleksej F. Filippov,et al.  Differential Equations with Discontinuous Righthand Sides , 1988, Mathematics and Its Applications.

[4]  Edgar Sanchez-Sinencio,et al.  Nonlinear switched capacitor 'neural' networks for optimization problems , 1990 .

[5]  Á. Rodríguez-Vázquez,et al.  Canonical non‐linear programming circuits , 1987 .

[6]  Michael Peter Kennedy,et al.  Unifying the Tank and Hopfield linear programming circuit and the canonical nonlinear programming circuit of Chua and Lin , 1987 .

[7]  Leon O. Chua,et al.  Pyramidal cells: a novel class of adaptive coupling cells and their applications for cellular neural networks , 1998 .

[8]  S. Sastry,et al.  A calculus for computing Filippov's differential inclusion with application to the variable structure control of robot manipulators , 1987 .

[9]  A. Tesi,et al.  New conditions for global stability of neural networks with application to linear and quadratic programming problems , 1995 .

[10]  Vadim I. Utkin,et al.  Sliding Modes and their Application in Variable Structure Systems , 1978 .

[11]  Jun Wang,et al.  A projection neural network and its application to constrained optimization problems , 2002 .

[12]  A. Bacciotti,et al.  Nonsmooth optimal regulation and discontinuous stabilization , 2003 .

[13]  G. Wilson.  Quadratic programming analogs , 1986 .

[14]  Sung Mo Kang,et al.  Section-wise piecewise-linear functions: Canonical representation, properties, and applications , 1977, Proceedings of the IEEE.

[15]  Edwin K. P. Chong,et al.  An analysis of a class of neural networks for solving linear programming problems , 1999, IEEE Trans. Autom. Control..

[16]  Xue-Bin Liang,et al.  A recurrent neural network for nonlinear continuously differentiable optimization over a compact convex subset , 2001, IEEE Trans. Neural Networks.

[17]  Zdzisław Denkowski,et al.  Set-Valued Analysis , 2021 .

[18]  Abdesselam Bouzerdoum,et al.  Neural network for quadratic optimization with bound constraints , 1993, IEEE Trans. Neural Networks.

[19]  Shankar Sastry,et al.  A calculus for computing Filippov's differential inclusion with application to the variable structure control of robot manipulators , 1986, 1986 25th IEEE Conference on Decision and Control.

[20]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[21]  Paolo Nistri,et al.  On open-loop and feedback attainability of a closed set for nonlinear control systems , 2002 .

[22]  G. Lin.  Nonlinear Programming without Computation , 2022 .

[23]  Jean-Pierre Aubin,et al.  Impulse differential inclusions: a viability approach to hybrid systems , 2002, IEEE Trans. Autom. Control..