Advertisement

Optimal Training Pattern Selection Using a Cluster-Generating Artificial Neural Network

  • T. Tambouratzis
  • D. G. Tambouratzis
Conference paper

Abstract

In this piece of research, the problem of optimal pattern selection for artificial neural network training is investigated. Given an initial set of training patterns, the objective is to extract the minimal subset which accurately represents the initial set.

The training pattern selection strategy which is presented here is based on the clustering capability of the Harmony Theory simulated-annealing harmony-maximisation artificial neural network [1]. Correction and reduction of the training set is achieved by rectifying the repetition and misclassification errors as well as by organising and unifying the training patterns in terms of their similarities.

Keywords

Artificial Neural Network Classification Error Input Pattern Training Pattern Pattern Selection 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Smolensky, P., (1986). Information Processing In Dynamical Systems: Foundations Of Harmony Theory pp. 194–281, in D.E. Rumelhart, J.L. McClelland (eds), “Parallel Distributed Processing: Foundations (Vol. 1)”. MIT Press, Cambridge.Google Scholar
  2. 2.
    Rumelhart, D.E., McClelland, J.L, (1986). “Parallel Distributed Processing: Explorations in the Microstructure of Cognition (vol. 1)”. MIT Press, Cambridge, MA.Google Scholar
  3. 3.
    Munro, P.W., (1992). Repeat Until Bored: A Pattern Selection Strategy in J.E. Moody, S.J. Hanson, R.P. Lippman (eds) “Advances in Neural Information Processing4, pp. 1001–1008. Morgan Kaufmann Publishers, San Mateo, CA.Google Scholar
  4. 4.
    Cachin, C, (1994). Pedagogical Pattern Selection Strategies, Neural Networks 7, pp. 175–181.CrossRefGoogle Scholar
  5. 5.
    Hwang, J.N., Choi, J.J., Seho, O.C., Marks, R.J., (1991). Query-based Learning Applied To Partially Trained Multilayered Perceptions, IEEE Transactions on Neural Networks 2, pp. 131–136.CrossRefGoogle Scholar
  6. 6.
    Tambouratzis, T., (1995). Simulated Annealing Artificial Neural Networks For The Satisfiability (SAT) Problem, in Proceedings of the “International Conference on Artificial Neural Networks and Genetic Algorithms — 1995”, Mines d’ Ales, France.Google Scholar
  7. 7.
    Tambouratzis, T., (1991). An Implementation Of A Harmony Theory Network For Interpreting Line Drawings, Network: Computation in Neural Systems 2, pp. 443–454.CrossRefGoogle Scholar
  8. 8.
    Tambouratzis, T., (1993). A Harmony Theory Network Solution To The Map-Coburing Problem, in Proceedings of the “International Joint Conference on Neural Networks 1993”, Nagoya, Japan, pp. 1545–1548.Google Scholar
  9. 9.
    Sabourin, M., Mitiche, A., (1993). Modelling And Classification Of Shape Using A Kohonen Associative Memory With Selective Multiresolution, Neural Networks 6, pp. 275–284.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • T. Tambouratzis
    • 1
  • D. G. Tambouratzis
    • 2
  1. 1.Institute of Informatics & TelecommunicationsNRCPS “Demokritos”Aghia ParaskeviGreece
  2. 2.Department of MathematicsAgricultural University of AthensAthensGreece

Personalised recommendations