A learning result for continuous-time recurrent neural networks

Systems and Control Letters

Volumn 34, Issue 3, 1998, Pages 151-158

  Sontag, Eduardo D ^a  

^a RUTGERS UNIVERSITY   (United States)

Author keywords

Computational learning theory; Recurrent neural networks; System identification

Indexed keywords

EID: 0012596163     PISSN: 01676911     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6911(98)00006-1     Document Type: Article

References (22)

1. F. Albertini, E.D. Sontag, For neural networks, function determines form, Neural Networks 6 (1993) 975-990.
2. F. Albertini, E.D. Sontag, State observability in recurrent neural networks, Systems Control Lett. 22 (1994) 235-244.
3. A.D. Back, A.C. Tsoi, FIR and UR synapses, a new neural network architecture for time-series modeling, Neural Comput. 3 (1991) 375-385.
4. Y. Bengio, Neural Networks for Speech and Sequence Recognition, Thompson Computer Press, Boston, 1996.
5. Y.-C. Chu, K. Glover, Bounds of the induced norm and model reduction errors for systems with repeated scalar nonlinearities, preprint, Cambridge University Department of Engineering, 1997.
6. B. Dasgupta, E.D. Sontag, Sample complexity for learning recurrent perceptron mappings, IEEE Trans. Inform. Theory 42 (1996) 1479-1487.
7. P. Goldberg, M. Jerrum, Bounding the Vapnik-Chervonenkis dimension of concept classes parametrized by real numbers, Machine Learning 18 (1995) 131-148.
8. D. Haussler, Decision theoretic generalizations of the PAC model for neural nets and other learning applications, Inform. Comput. 100 (1992) 78-150.
9. M. Karpinski, A. Macintyre, Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks, J. Comput. System Sci., to appear. (Summary in: Polynomial bounds for VC dimension of sigmoidal neural networks, in: Proc. 27th ACM Symp. on Theory of Computing, 1995, pp. 200-208.)
10. M. Karpinski, A. Macintyre, Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks, J. Comput. System Sci., to appear. (Summary in: Polynomial bounds for VC dimension of sigmoidal neural networks, in: Proc. 27th ACM Symp. on Theory of Computing, 1995, pp. 200-208.)
11. P. Koiran, E.D. Sontag, Vapnik-Chervonenkis dimension of recurrent neural networks, in: Proc. 3rd European Conf. on Computational Learning Theory, Jerusalem, March 1997, to appear.
12. M. Matthews, A state-space approach to adaptive nonlinear filtering using recurrent neural networks, in: Proc. IASTED Symp. on Artificial Intelligence Applications and Neural Networks, Zürich, July 1990, pp. 197-200.
13. M.M. Polycarpou, P.A. Ioannou, Neural networks and on-line approximators for adaptive control, in: Proc. 7th Yale Workshop on Adaptive and Learning Systems, Yale University, 1992, pp. 93-798.
14. H.T. Siegelmann, E.D. Sontag, Turing computability with neural nets, Appl. Math. Lett. 4 (6) (1991) 77-80.
15. E.D. Sontag, Mathematical Control Theory: Deterministic Finite Dimensional Systems, Springer, New York, 1990.
16. E.D. Sontag, Neural networks for control, in: H.L. Trentelman, J.C. Willems (Eds.), Essays on Control: Perspectives in the Theory and its Applications, Birkhauser, Boston, 1993, pp. 339-380.
17. E.D. Sontag, Recurrent neural networks: some systems-theoretic aspects, in: M. Karny, K. Warwick, V. Kurkova (Eds.), Dealing with Complexity: a Neural Network Approach, Springer, London, 1998, to appear.
18. E.D. Sontag, H.J. Sussmann, Complete controllability of continuous-time recurrent neural networks, Systems Control Lett. 30 (4) (1997) 177-183.
19. V.N. Vapnik, Estimation of Dependencies Based on Empirical Data, Springer, Berlin, 1982.
20. M. Vidyasagar, A Theory of Learning and Generalization: With Applications to Neural Networks and Control Systems, Springer, London, 1997.
21. R. Zbikowski, Lie algebra of recurrent neural networks and identifiability, in: Proc. Amer. Automatic Control Conference, San Francisco, 1993, pp. 2900-2901.
22. R. Zbikowski, K.J. Hunt (Eds.), Neural Adaptive Control Technology, World Scientific, Singapore, 1996.