Abstract
This paper considers learning a dynamical system (DS) by a recurrent neural network (RNN). We propose an affine neural dynamical system (A-NDS) as a DS that an RNN actually produces on the output space to approximate a target DS. We present a unique parametric representation of A-NDSs using RNNs and affine sections with the aim of constructing effective learning algorithms.
Preview
Unable to display preview. Download preview PDF.
References
Baldi, P., Gradient descent learning algorithm overview: A general dynamical systems perspective, IEEE Transactions on Neural Networks 6 (1995), 182–195.
Hertz, J., Krogh, A., and Palmer, R. G., Introduction to the Theory of Neural Computation. Addison Wesley, 1991.
Hirsh, M. W., and Smale, S., Differential Equations, Dynamical Systems and Linear Algebra. Academic Press, 1974.
Hornik, K., Stinchcombe, M., and White, H., Multilayer feedforward networks are universal approximators, Neural Networks 2 (1989), 359–366.
Kimura, M., and Nakano, R., Learning dynamical systems from trajectories by continuous time recurrent neural networks, Proceedings of 1995 IEEE International Conference on Neural Networks 6 (1995), 2992–2997.
Kimura, M., and Nakano, R., Learning dynamical systems produced by recurrent neural networks, Proceedings of 1996 International Conference on Artificial Neural Networks (1996), 133–138.
Sussmann, H. J., Uniqueness of the weights for minimal feedforward nets with a given input-output map, Neural Networks 5 (1992), 589–593.
Tsung, F-S., and Cottrell, G. W., Phase-space learning, Advances in Neural Information Processing Systems 7 (1995), 481–488.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kimura, M., Nakano, R. (1997). Unique representations of dynamical systems produced by recurrent neural networks. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020188
Download citation
DOI: https://doi.org/10.1007/BFb0020188
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive