Self-Organizing Neural Networks for Signal Recognition

  • Jan Koutník
  • Miroslav Šnorek
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4131)

Abstract

In this paper we introduce a self-organizing neural network that is capable of recognition of temporal signals. Conventional self-organizing neural networks like recurrent variant of Self-Organizing Map provide clustering of input sequences in space and time but the identification of the sequence itself requires supervised recognition process, when such network is used. In our network called TICALM the recognition is expressed by speed of convergence of the network while processing either learned or an unknown signal. TICALM network capabilities are shown on an experiment with handwriting recognition.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baier, V.: Motion Processing and Prediction With a Hierarchical RSOM based Model. In: Proceedings of the IJCNN 2005 (2005)Google Scholar
  2. 2.
    Barreto, G.A., Araujo, A.F.R., Kremer, S.: A taxonomy for spatiotemporal connectionist networks revisited: The unsupervised case. Neural Computation 15(6), 1255–1320 (2003)MATHCrossRefGoogle Scholar
  3. 3.
    Elman, J.L.: Finding structure in time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
  4. 4.
    Gers, F.A., Schmidhuber, J.: LSTM recurrent networks learn simple context free and context sensitive languages. IEEE Transactions on Neural Networks 12(6), 1333–1340 (2001)CrossRefGoogle Scholar
  5. 5.
    Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer, Heidelberg (2001), ISBN 3-540-67921-9MATHGoogle Scholar
  6. 6.
    Koutník, J., Šnorek, M.: Neural Network Generating Hidden Markov Chain, in Adaptive and Natural Computing Algorithms. In: Proceedings of the International Conference in Coimbra, pp. 518–521. Springer, Wien (2005), ISBN 3-211-24934-6Google Scholar
  7. 7.
    Koutník, J., Šnorek, M.: Single Categorizing and Learning Module for Temporal Sequences. In: Proceedings of the International Joint Conference on Neural Networks, pp. 2977–2982. IEEE, Piscataway (2004), ISBN 0-7803-8360-5Google Scholar
  8. 8.
    Lampinen, J., Oja, E.: On Clustering Properties of Hierarchical Self-Organizing Maps. Journal of Mathematical Imaging and Vision 2(2-3), 261–272 (1992)MATHCrossRefGoogle Scholar
  9. 9.
    Maass, W.: Networks of Spiking Neurons: The Third Generation of Neural Network Models. Neural Networks 10(9), 1659–1671 (1997)CrossRefGoogle Scholar
  10. 10.
    Murre J.M.J., Phaf R.H., Wolters G., CALM: Categorizing and Learning Module, Neural Networks, Vol. 5, pp. 55-82, Pergamon Press 1992Google Scholar
  11. 11.
    Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE 77(2) (February 1989)Google Scholar
  12. 12.
    Principe, J., Euliano, N., Garani, S.: Principles and networks for self-organization in space-time. Neural Networks 15(8-9), 1069–1083 (2002)CrossRefGoogle Scholar
  13. 13.
    Tijsseling, A.G.: Sequential Information Processing using Time-Delay Connections in Ontogenic CALM networks. IEEE Transactions on Neural Networks 16(1), 145–159 (2005), ISSN: 1045-9227CrossRefGoogle Scholar
  14. 14.
    Varsta, M.: Self Organizing Maps in Sequence Processing, Dissertation Thesis, Helsinki University of Technology (2002), ISBN 951-22-6251-7Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jan Koutník
    • 1
  • Miroslav Šnorek
    • 1
  1. 1.Department of Computer Science and EngineeringCzech Technical UniversityPragueCzech Republic

Personalised recommendations