Dynamical Systems Produced by Recurrent Neural Networks

Systems and Computers in Japan

Volumn 31, Issue 4, 2000, Pages 77-86

  Kimura, Masahiro ^a   Nakano, Ryohei ^a  

^a NTT Communication Science Laboratories   (Japan)

Author keywords

Affine neural dynamical system; Dynamical system learning; Hidden unit; Neural dynamical system; Recurrent neural network

Indexed keywords

EID: 0043184308     PISSN: 08821666     EISSN: None     Source Type: Journal    
DOI: 10.1002/(SICI)1520-684X(200004)31:4<77::AID-SCJ8>3.0.CO;2-Y     Document Type: Article

References (23)

1. Hertz J, Krogh A, Palmer RG. Introduction to the theory of neural computation. Addison-Wesley; 1991.
2. Pineda FJ. Generalization of back-propagation to recurrent neural networks. Phys Rev Lett 1987;59:2229-2232.
3. Doya K, Yoshizawa S. Adaptive neural oscillator using continuous time back-propagation learning. Neural Networks 1989;2:375-385.
4. Pearlmutter BA. Learning state space trajectories in recurrent neural networks. Neural Computation 1989;1:263-269.
5. Sato M. A learning algorithm to teach spatiotemporal patterns to recurrent neural networks. Biol Cybern 1990;62:259-263.
6. Sato M, Joe K, Hirahara T. APOLONN brings us to the real world. Proc IJCNN'90, p 581-587.
7. Sun GZ, Chen HH, Lee YC. Green function method for fast on-line learning algorithm of recurrent neural networks. In: Moody JE, et al. editors. Advances in neural information processing systems, Vol. 4. Morgan Kaufmann; 1992. p 333-340.
8. Toomarian NB, Barhen J. Learning a trajectory using adjoint functions and teacher forcing. Neural Networks 1992;5:473-484.
9. Bersini H, Saerens M, Sotelino LG. Hopfield net generation, encoding and classification of temporal trajectories. IEEE Trans Neural Networks 1994;5:945-953.
10. Sotelino LG, Saerens M, Bersini H. Classification of temporal trajectories by continuous time recurrent nets. Neural Networks 1994;7:767-776.
11. Baldi P. Gradient descent learning algorithm overview: A general dynamical systems perspective. IEEE Trans Neural Networks 1995;6:182-195.
12. Hirsh MW, Smale S. Differential equations, dynamical systems and linear algebra. Academic Press; 1974.
13. Hofbauer J, Sigmund K. The theory of evolution and dynamical systems. Cambridge University Press; 1988.
14. Sato M, Murakami Y, Joe K. Learning chaotic dynamics by recurrent neural networks. Proc Int Conf Fuzzy Logic and Neural Networks, p 601-604, 1990.
15. Tsung FS, Cottrell GW. Phase-space learning. In: Tesauro G, et al., editors. Advances in neural information processing systems, Vol. 7. MIT Press; 1995. p 481-488.
16. Nakajima H, Ueda Y. An analysis of the process of learning continuous dynamical systems in neural networks using the theory of non-autonomous difference evaluation. Denshi Joho Tsushin Gakkai Ronbunshi 1995;J78-D-II:1890-1898. (in Japanese)
17. Funahashi K., Nakamura Y. Approximation of dynamical systems by continuous time recurrent neural networks. Neural Networks 1993;6:801-806.
18. Funahashi K. Approximation theory, dynamical systems, and recurrent neural networks. Proc 5th Int Colloq Differential Equations 1994;2:51-58.
19. Amari S. Mathematics of neural networks. Sangyotosho; 1978. (in Japanese)
20. Beer RD. On the dynamics of small continuous-time recurrent neural networks. Adaptive Behavior 1995;3:469-509.
21. Cybenko G. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems 1989;2:303-314.
22. Funahashi K. On the approximate realization of continuous mappings by neural networks. Neural Networks 1989;2:183-191.
23. Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks 1989;2:359-366.