Further results on controllability of recurrent neural networks 1 1 Supported in part by US Air Forc

This paper studies controllability properties of recurrent neural networks. The new contributions are: (1) an extension of a previous result to a slightly different model, (2) a formulation and proof of a necessary and sufficient condition, and (3) an analysis of a low-dimensional case for which the hypotheses made in previous work do not apply.

[1]  Eduardo Sontag,et al.  For neural networks, function determines form , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[2]  Eduardo D. Sontag,et al.  Neural Networks for Control , 1993 .

[3]  Michael Athans,et al.  Nonlinear and Adaptive Control , 1989 .

[4]  H. Sussmann,et al.  Local controllability and motion planning for some classes of systems with drift , 1991, [1991] Proceedings of the 30th IEEE Conference on Decision and Control.

[5]  C. Lee Giles,et al.  Higher Order Recurrent Networks and Grammatical Inference , 1989, NIPS.

[6]  A. Michel,et al.  Uniqueness and stability of equilibria of a class of neural networks with applications to the Hopfield model , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[7]  Eduardo D. Sontag,et al.  For neural networks, function determines form , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

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

[9]  P. D. Pra,et al.  Forward accessibility for recurrent neural networks , 1995, IEEE Trans. Autom. Control..

[10]  D. Mayne.  Nonlinear and Adaptive Control Design [Book Review] , 1996, IEEE Transactions on Automatic Control.

[11]  Eduardo D. Sontag,et al.  Finite-dimensional open-loop control generators for non-linear systems , 1988 .

[12]  Eduardo D. Sontag,et al.  Mathematical Control Theory: Deterministic Finite Dimensional Systems , 1990 .

[13]  Yun-Chung Chu,et al.  Gain-scheduling for systems with repeated scalar nonlinearities , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[14]  Eduardo D. Sontag,et al.  Recurrent Neural Networks: Some Systems-Theoretic Aspects , 1997 .

[15]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

[16]  H. Sussmann,et al.  Global controllability by nice controls , 1990 .

[17]  Rafal Zbikowski.  Lie Algebra of Recurrent Neural Networks and Identifiability , 1993, 1993 American Control Conference.

[18]  Eduardo D. Sontag,et al.  Complete controllability of continuous-time recurrent neural networks , 1997 .