Neural Network Generating Hidden Markov Chain

  • J. Koutník
  • M. Šnorek
Conference paper


In this paper we introduce technique how a neural network can generate a Hidden Markov Chain. We use neural network called Temporal Information Categorizing and Learning Map. The network is an enhanced version of standard Categorizing and Learning Module (CALM). Our modifications include Euclidean metrics instead of weighted sum formerly used for categorization of the input space. Construction of the Hidden Markov Chain is provided by turning steady weight internal synapses to associative learning synapses. Result obtained from testing on simple artificial data promises applicability in a real problem domain. We present a visualization technique of the obtained Hidden Markov Chain and the method how the results can be validated. Experiments are being performed.


Neural Network Hide Markov Model Input Vector Input Space Arousal Process 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Elman J.L., Finding structure in time. Cognitive Science, 14, pp. 179–211. 1990CrossRefGoogle Scholar
  2. [2]
    Maass W., Networks of Spiking Neurons: The Third Generation of Neural Network Models, Neural Networks 10(9), pp. 1659–1671, 1997CrossRefGoogle Scholar
  3. [3]
    Gers F.A., Schmidhuber J., LSTM recurrent networks learn simple context free and context sensitive languages. IEEE Transactions on Neural Networks, 12(6), pp. 1333–1340, 2001.CrossRefGoogle Scholar
  4. [4]
    Rabiner L.R., A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, in Proceedings of the IEEE, vol.77, No.2, Feb 1989.Google Scholar
  5. [5]
    Morita M., Oliveira L. S., Sabourin R., Bortolozzi F., Suen C. Y., An HMM-MLP Hybrid System to Recognize Handwritten Dates. International Joint Conference on Neural Networks, (ICJNN’02), pp. 867–872, Honolulu-USA, May 12–17, 2002.Google Scholar
  6. [6]
    Murre J.M.J., Phaf R.H., Wolters G., CALM: Categorizing and Learning Module, Neural Networks, Vol. 5, pp. 55–82, Pergamon Press 1992CrossRefGoogle Scholar
  7. [7]
    Koutník J., Šorek M., Single Categorizing and Learning Module for Temporal Sequences, in Proceedings of the International Joint Conference on Neural Networks (IJCNN’04), Budapest, July 25–29, 2004.Google Scholar

Copyright information

© Springer-Verlag/Wien 2005

Authors and Affiliations

  • J. Koutník
    • 1
  • M. Šnorek
    • 1
  1. 1.Neural Computing Group, Department of Computer Science and EngineeringCzech Technical UniversityPragueCzech Republic

Personalised recommendations