论文信息 - State observability in recurrent neural networks - 字舞流文

State observability in recurrent neural networks

We obtain a characterization of observability for a class of nonlinear systems which appear in neural networks research.<<ETX>>

Eduardo D. Sontag | Francesca Albertini

[1] Héctor J. Sussmann,et al. Uniqueness of the weights for minimal feedforward nets with a given input-output map , 1992, Neural Networks.

[2] Eduardo D. Sontag,et al. UNIQUENESS OF WEIGHTS FOR NEURAL NETWORKS , 1993 .

[3] Stephen P. Boyd,et al. Uniqueness of circuits and systems containing one nonlinearity , 1985 .

[4] Anders Krogh,et al. Introduction to the theory of neural computation , 1994, The advanced book program.

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

[6] Hava T. Siegelmann,et al. Some recent results on computing with 'neural nets' , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

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

[8] M. B. Reed,et al. Realization Theory of Discrete-Time Nonlinear Systems: Part I - The Bounded Case , 1979 .

[9] Wilson J. Rugh,et al. On the structure of a class of nonlinear systems , 1973, CDC 1973.

[10] Hava T. Siegelmann,et al. Some results on computing with `neural nets , 1992 .

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