Generalization in Learning Multiple Temporal Patterns Using RNNPB

  • Masato Ito
  • Jun Tani
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)

Abstract

This paper examines the generalization capability in learning multiple temporal patterns by the recurrent neural network with parametric bias (RNNPB). Our simulation experiments indicated that the RNNPB can learn multiple patterns as generalized by extracting relational structures shared among the training patterns. It was, however, shown that such generalizations cannot be achieved when the relational structures are complex. Our analysis clarified that the qualitative differences appear in the self-organized internal structures of the network between generalized cases and not-generalized ones.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jordan, M.: Attractor dynamics and parallelism in a connectionist sequential machine. In: Proc. of Eighth Annual Conference of Cognitive Science Society, pp. 531–546. Erlbaum, Hillsdale (1986)Google Scholar
  2. 2.
    Wolpert, D., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Networks 11, 1317–1329 (1998)CrossRefGoogle Scholar
  3. 3.
    Tani, J., Nolfi, S.: Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems. In: Pfeifer, R., Blumberg, B., Meyer, J., Wilson, S. (eds.) From animals to animats 5. MIT Press, Cambridge (1998); later published in Neural Networks 12, 1131–1141 (1999)Google Scholar
  4. 4.
    Tani, J., Ito, M.: Self-organization of behavioral primitives as multiple attractor dynamics: a robot experiment. IEEE Trans. on Sys. Man and Cybern. Part A 33, 481–488 (2003)CrossRefGoogle Scholar
  5. 5.
    Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation. In: Rumelhart, D., Mclelland, J. (eds.) Parallel Distributed Processing, pp. 318–362. MIT Press, Cambridge (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Masato Ito
    • 1
  • Jun Tani
    • 2
  1. 1.Sony CorporationTokyoJapan
  2. 2.RIKENBrain Science InstituteSaitamaJapan

Personalised recommendations