Stability analysis for a class of neural networks

This paper considers the problem of characterizing the stability properties of the equilibria of an important class of recurrent neural networks. Sufficient conditions are given under which the neural network possesses a unique globally asymptotically stable equilibrium point for each external input. These conditions are less restrictive than those previously obtained and are easily checked, so that incorporating them in existing neural network design procedures should increase the flexibility and reduce the complexity of this synthesis process. Results are provided for both continuous-time and discrete-time networks.

[1]  Eduardo D. Sontag,et al.  Feedback Stabilization Using Two-Hidden-Layer Nets , 1991, 1991 American Control Conference.

[2]  Anthony N. Michel,et al.  Analysis and synthesis techniques for Hopfield type synchronous discrete time neural networks with application to associative memory , 1990 .

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

[4]  Laura I. Burke,et al.  An unsupervised neural network approach to tool wear identification , 1993 .

[5]  David Dornfeld,et al.  Pattern recognition of acoustic emission signals during punch stretching , 1987 .

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

[7]  M. Vidyasagar,et al.  Qualitative Analysis of Large Scale Dynamical Systems , 2012, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Helge J. Ritter,et al.  Three-dimensional neural net for learning visuomotor coordination of a robot arm , 1990, IEEE Trans. Neural Networks.

[9]  Richard Colbaugh,et al.  Real-time tool wear estimation using cutting force measurements , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

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

[11]  Mahesan Niranjan,et al.  A theoretical investigation into the performance of the Hopfield model , 1990, IEEE Trans. Neural Networks.

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

[13]  Liang Jin,et al.  Direct adaptive output tracking control using multilayered neural networks , 1993 .

[14]  J. Farrell,et al.  Qualitative analysis of neural networks , 1988, 1988., IEEE International Symposium on Circuits and Systems.

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

[16]  Sandeep Gulati,et al.  Neutral learning of constrained nonlinear transformations , 1989, Computer.

[17]  Malur K. Sundareshan,et al.  Equilibrium characterization of dynamical neural networks and a systematic synthesis procedure for associative memories , 1991, IEEE Trans. Neural Networks.

[19]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[20]  Allon Guez,et al.  On the stability, storage capacity, and design of nonlinear continuous neural networks , 1988, IEEE Trans. Syst. Man Cybern..

[21]  Kenneth Kreutz-Delgado,et al.  Learning Global Direct Inverse Kinematics , 1991, NIPS.