Advertisement

Unique representations of dynamical systems produced by recurrent neural networks

  • Masahiro Kimura
  • Ryohei Nakano
Part III: Learning: Theory and Algorithms
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1327)

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.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baldi, P., Gradient descent learning algorithm overview: A general dynamical systems perspective, IEEE Transactions on Neural Networks 6 (1995), 182–195.Google Scholar
  2. 2.
    Hertz, J., Krogh, A., and Palmer, R. G., Introduction to the Theory of Neural Computation. Addison Wesley, 1991.Google Scholar
  3. 3.
    Hirsh, M. W., and Smale, S., Differential Equations, Dynamical Systems and Linear Algebra. Academic Press, 1974.Google Scholar
  4. 4.
    Hornik, K., Stinchcombe, M., and White, H., Multilayer feedforward networks are universal approximators, Neural Networks 2 (1989), 359–366.Google Scholar
  5. 5.
    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.Google Scholar
  6. 6.
    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.Google Scholar
  7. 7.
    Sussmann, H. J., Uniqueness of the weights for minimal feedforward nets with a given input-output map, Neural Networks 5 (1992), 589–593.Google Scholar
  8. 8.
    Tsung, F-S., and Cottrell, G. W., Phase-space learning, Advances in Neural Information Processing Systems 7 (1995), 481–488.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Masahiro Kimura
    • 1
  • Ryohei Nakano
    • 1
  1. 1.NTT Communication Science LaboratoriesKyotoJapan

Personalised recommendations