New conditions for global stability of neural networks with application to linear and quadratic programming problems

In this paper, we present new conditions ensuring existence, uniqueness, and Global Asymptotic Stability (GAS) of the equilibrium point for a large class of neural networks. The results are applicable to both symmetric and nonsymmetric interconnection matrices and allow for the consideration of all continuous nondecreasing neuron activation functions. Such functions may be unbounded (but not necessarily surjective), may have infinite intervals with zero slope as in a piece-wise-linear model, or both. The conditions on GAS rely on the concept of Lyapunov Diagonally Stable (or Lyapunov Diagonally Semi-Stable) matrices and are proved by employing a class of Lyapunov functions of the generalized Lur'e-Postnikov type. Several classes of interconnection matrices of applicative interest are shown to satisfy our conditions for GAS. In particular, the results are applied to analyze GAS for the class of neural circuits introduced for solving linear and quadratic programming problems. In this application, the principal result here obtained is that these networks are GAS also when the constraint amplifiers are dynamical, as it happens in any practical implementation. >

[1]  R. Palais.  Natural operations on differential forms , 1959 .

[2]  J. Milnor.  Topology from the differentiable viewpoint , 1965 .

[3]  M. Fiedler,et al.  Some generalizations of positive definiteness and monotonicity , 1966 .

[4]  B. Anderson.  A SYSTEM THEORY CRITERION FOR POSITIVE REAL MATRICES , 1967 .

[5]  Dragoslav D. Šiljak,et al.  Nonlinear systems;: The parameter analysis and design , 1968 .

[6]  E. Kuh,et al.  Some results on existence and uniqueness of solutions of nonlinear networks , 1971 .

[7]  I. W. Sandberg,et al.  Existence and Uniqueness of Solutions for the Equations of Nonlinear DC Networks , 1972 .

[8]  C. Desoer.  Frequency domain criteria for absolute stability , 1975, Proceedings of the IEEE.

[9]  L. Chua,et al.  On the application of degree theory to the analysis of resistive nonlinear networks , 1977 .

[10]  Dragoslav D. Šiljak,et al.  Large-Scale Dynamic Systems: Stability and Structure , 1978 .

[11]  L. Chua.  Dynamic nonlinear networks: State-of-the-art , 1980 .

[12]  Leon O. Chua,et al.  Device modeling via nonlinear circuit elements , 1980 .

[13]  H. Khalil.  On the existence of positive diagonal P such that PA + A^{T}P l 0 , 1982 .

[14]  Abraham Berman,et al.  Matrix Diagonal Stability and Its Implications , 1983 .

[15]  M. Hirsch.  Systems of Differential Equations that are Competitive or Cooperative II: Convergence Almost Everywhere , 1985 .

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

[17]  Brian D. O. Anderson,et al.  Stability of adaptive systems: passivity and averaging analysis , 1986 .

[18]  P. Khargonekar,et al.  Stability robustness bounds for linear state-space models with structured uncertainty , 1987 .

[19]  Hui Hu,et al.  An algorithm for rescaling a matrix positive definite , 1987 .

[20]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

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

[22]  D. Siljak.  Parameter Space Methods for Robust Control Design: A Guided Tour , 1988, 1988 American Control Conference.

[23]  A. Michel,et al.  Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercube , 1989 .

[24]  Morris W. Hirsch,et al.  Convergent activation dynamics in continuous time networks , 1989, Neural Networks.

[25]  William A. Brock,et al.  Differential Equations, Stability and Chaos in Dynamic Economics , 1989 .

[26]  D. Kelly,et al.  Stability in contractive nonlinear neural networks , 1990, IEEE Transactions on Biomedical Engineering.

[27]  Leon O. Chua,et al.  Stability of a class of nonreciprocal cellular neural networks , 1990 .

[28]  Anthony N. Michel,et al.  Analysis and synthesis of neural networks with lower block triangular interconnecting structure , 1990, 29th IEEE Conference on Decision and Control.

[29]  Mauro Forti,et al.  On a class of nonsymmetrical neural networks with application to ADC , 1991 .

[30]  M. Forti,et al.  A condition for global convergence of a class of symmetric neural circuits , 1992 .

[31]  Michael A. Shanblatt,et al.  Linear and quadratic programming neural network analysis , 1992, IEEE Trans. Neural Networks.

[32]  Kiyotoshi Matsuoka.  Absolute stability of neural networks , 1992, Systems and Computers in Japan.

[33]  Daniel Hershkowitz,et al.  Recent directions in matrix stability , 1992 .

[34]  Leon O. Chua,et al.  Stability analysis of generalized cellular neural networks , 1993, Int. J. Circuit Theory Appl..

[35]  Eduardo F. Camacho,et al.  Neural network for constrained predictive control , 1993 .

[36]  Munther A. Dahleh,et al.  An overview of extremal properties for robust control of interval plants , 1993, Autom..

[37]  B. Ross Barmish,et al.  New Tools for Robustness of Linear Systems , 1993 .

[38]  A. Michel,et al.  Robustness and Perturbation Analysis of a Class of Nonlinear Systems with Applications to Neural Networks , 1993, 1993 American Control Conference.

[39]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[40]  M. Forti.  On Global Asymptotic Stability of a Class of Nonlinear Systems Arising in Neural Network Theory , 1994 .

[41]  M. Forti,et al.  Necessary and sufficient condition for absolute stability of neural networks , 1994 .

[42]  Mauro Forti,et al.  On absolute stability of neural networks , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.