Local stability of recurrent networks with time-varying weights and inputs

Abstract We present local conditions for stability of recurrent neural networks with time-varying parameters. Our constructive approach guarantees that a recurrent network implements a proper mapping from time-varying input to time-varying output functions using a local equilibrium as point of operation. The corresponding bounds on the allowed inputs and time-variation are defined by linear matrix inequalities and can be obtained numerically efficient by means of interior point optimisation schemes. We compare the method to the standard Lyapunov approach and apply it to an example of learning an input–output map implied by the chaotic Roessler attractor.

[1]  Herbert Witte,et al.  Learning continuous trajectories in recurrent neural networks with time-dependent weights , 1999, IEEE Trans. Neural Networks.

[2]  A. Michel,et al.  Exponential stability and trajectory bounds of neural networks under structural variations , 1990, 29th IEEE Conference on Decision and Control.

[3]  Jochen J. Steil.  Local input-output stability of recurrent networks with time-varying weights , 2000, ESANN.

[4]  Yuguang Fang,et al.  Stability analysis of dynamical neural networks , 1996, IEEE Trans. Neural Networks.

[5]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.

[6]  Heiko Wersing,et al.  A Competitive-Layer Model for Feature Binding and Sensory Segmentation , 2001, Neural Computation.

[7]  Anjan Bose,et al.  Qualitative Analysis of Large‐Scale Systems: Stability, Instability and Boundedness , 1976 .

[8]  David H. Owens,et al.  Existence, learning, and replication of periodic motions in recurrent neural networks , 1998, IEEE Trans. Neural Networks.

[9]  Helge J. Ritter,et al.  Maximisation of stability ranges for recurrent neural networks subject to on-line adaptation , 1999, ESANN.

[10]  Yuguang Fang,et al.  Sufficient conditions for the stability of interval matrices , 1993 .

[11]  Kiyotoshi Matsuoka,et al.  Stability conditions for nonlinear continuous neural networks with asymmetric connection weights , 1992, Neural Networks.

[12]  Jochen J. Steil,et al.  Input output stability of recurrent neural networks , 1999 .

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

[14]  H. Ritter,et al.  Recurrent learning of input-output stable behaviour in function space: A case study with the Roessler attractor , 1999 .

[15]  Barak A. Pearlmutter.  Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[16]  A. Michel,et al.  On the stability of a family of nonlinear time-varying systems , 1996 .

[17]  Yuichi Nakamura,et al.  Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.