Retraining and redundancy elimination for a Condensed Nearest Neighbour network

  • Dieter Barschdorff
  • Achim Bothe
  • Ulrich Gärtner
  • Andreas Jäger
Neural Networks
Part of the Lecture Notes in Computer Science book series (LNCS, volume 604)


A new method of supervised retraining for an artificial neural network model based on the Condensed-Nearest-Neighbour classification principle is presented. Adaptation to time variable features and the classification of new occured objects is possible now. Furthermore different approaches for the elimination of redundant training patterns to reduce the size of the training set and the time required for training and classification is achieved. A speech recognition system is presented as an example of application.


Neural network retraining adaptive structure speech recognition 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Barschdorff, D.: Case Studies in Adaptive Fault Diagnosis using Neural Networks. Proc. of the IMACS Annals on Computing and Applied Mathematics, MIM-S2, 3.–7. Sept. 1990, Brüssels, pp. III.A.1/1-1/6Google Scholar
  2. [2]
    Barschdorff, D.: Adaptive Failure Diagnosis using Neural Networks. 7th Symposium on Technical Diagnostics, Helsinki, Finnland, 17.–20. Sept. 1990Google Scholar
  3. [3]
    Barschdorff, D., Becker, D.: Neural Networks as Signal and Pattern Classifiers. Technisches Messen tm 57, 11/1990, pp. 437–444, Oldenbourg Verlag, MünchenGoogle Scholar
  4. [4]
    Barschdorff, D., Cai X, Wöstenkühler, G.: A Learning Pattern Recognition Method for Acoustical Quality Control of Fan Motors. Automatisierungstechnik at 39, 2/1991, pp. 43–48, Oldenbourg Verlag, MünchenGoogle Scholar
  5. [5]
    Carpenter, G.A., Grossberg, S.: The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network. Computer 21 (1988), pp. 77–88CrossRefGoogle Scholar
  6. [6]
    DARPA Neural Network Study. AFCEA International Press, Fairfax (Virginia), USA, 1988Google Scholar
  7. [7]
    Ersoy, O. K.; Hong, D.: Parallel, Self-Organizing, Hierarchical Neural Networks. IEEE Transactions on Neural Networks, Vol. 1, No. 2, June 1990Google Scholar
  8. [8]
    Fukushima, K.: Neocognitron: A Self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position. Biological Cybernetics 36, 1980, pp. 193–202CrossRefPubMedGoogle Scholar
  9. [9]
    Gramss, T.; Strube, H.W.: Recognition of isolated words by extracting invariant features, NSMS-Symposium, 1990Google Scholar
  10. [10]
    Gramss, T.; Strube, H.W.:Recognition of isolated words based on psychoacustics and neurobiology, Speech Communication, Elsevier, oNorth-Holland, 1990, pp. 35–40Google Scholar
  11. [11]
    Hart, P.E.: The Condensed Nearest Neighbour Rule. IEEE Transactions on Information Theory 14, 1968, pp. 515–516CrossRefGoogle Scholar
  12. [12]
    Hartigan, J.A.: Clustering Algorithms. John Wiley & Sons, New York, 1975Google Scholar
  13. [13]
    Krause, A.; Hackbarth, H.: Scaly Artificial Neural Networks for Speaker-Independent Recognition of Isolated Words, IEEE ICASSP 1989Google Scholar
  14. [14]
    Kohonen, T.; Riittinen, H.; Reuhkala, E.; Haltsonen, S.: On-Line Recognition of Spoken Words from a Large Vocabulary, Information Sciences 33, Elsevier, 1984, pp. 3–30CrossRefGoogle Scholar
  15. [15]
    Lippmann, R.P.; Gold, B.: Neural-Net classifiers useful for speech recognition, Proc. IEEE First Intern. Conference on Neural Networks, San Diego, 1987Google Scholar
  16. [16]
    Lippmann, R.P.: An Introduction to Computing with Neural Nets. IEEE ASSP Magazine, Vol. 4, No. 2, April 1987Google Scholar
  17. [17]
    McClelland, J.L., Rumelhart, D.E.: Explorations in Parallel Distributed Processing. MIT Press, Cambridge 1986Google Scholar
  18. [18]
    Murphy, O.J.: Nearest Neighbour Pattern Classification Perceptrons. Proceedings of the IEEE, Vol. 78, No. 10, October 1990Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Dieter Barschdorff
    • 1
  • Achim Bothe
    • 1
  • Ulrich Gärtner
    • 1
  • Andreas Jäger
    • 1
  1. 1.Institute of Electrical MeasurementUniversity of PaderbornPaderborn

Personalised recommendations