Advertisement

Quasi-optimum combination of multilayer perceptrons for adaptive multiclass pattern recognition

  • Alberto Ruiz García
  • Francisco J. Arcas Túnez
Neural Networks for Perception
Part of the Lecture Notes in Computer Science book series (LNCS, volume 930)

Abstract

Standard multiclass pattern recognition requires frequent re-learning stages when the set of categories of interest evolves in time. In order to minimize the computation costs of class incorporation and removal, we divide the global multiclass recognizer into a collection of class pairwise neural dichotomizers. When a new class appears, an adequate set of dichotomizers is created and trained to discriminate the new class from the rest. If a class disappears, its associated dichotomizers are eliminated In both cases previously learned knowledge is not disturbed. The properties of neural recognizers and pairwise modularization allow an analytic quasi-optimum method for combining network outputs to obtain the global multiclass response. An incremental and distributed pattern recognition architecture is presented and its performance experimentally evaluated, obtaining better error rates and learning times than conventional multiclass recognizers using similar resources. The design is highly parallel and asyncronous, adequate for dynamic real time applications.

Keywords

pattern classification neural networks density estimation data fusion classifiers combination 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Bibliography

  1. [1]
    A. Abidi, R. C. Gonzalez (eds.), Data Fusion: In Robotics and Machine Intelligence, Academic Press, 1992.Google Scholar
  2. [2]
    F. J. Arcas Túnez. Descomposición de Reconocedores de Patrones Multiclase, Term Project, Facultad de Informática, Universidad de Murcia, Spain, December 1993 (in Spanish).Google Scholar
  3. [3]
    W. G. Baxt, “Improving the Accuracy of an Artificial Neural Network Using Multiple Differently Trained Networks”, Neural Computation, 4, 772–780 (1992)Google Scholar
  4. [4]
    J. S. Denker, Y. leCun, “Transforming Neural-Net Output Levels to Probability Distributions” Adv. Neur. Inf. 3, Morgan Kaufmann 1991Google Scholar
  5. [5]
    R. O. Duda, P. E. Hart, Pattern Classification and Scene Analysis, John Wiley & Sons, 1973Google Scholar
  6. [6]
    K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press, 1990Google Scholar
  7. [7]
    J. Hertz, A. Krogh, R.G. Palmer, Introduction to the Theory of Neural Computation, Addison Wesley 1991Google Scholar
  8. [8]
    T. K. Ho, J. J. Hull, S. N. Srihari, “Decision Combination in Multiple Classifier Systems”, IEEE T. on Pattern Analysis and Machine Intelligence, V16 N1 Jan 1994, pp. 66–75Google Scholar
  9. [9]
    K. Hornik, M. Stinchcombe, H. White, “Multilayer Feed Forward Networks are Universal Approximators”, Neural Networks N2, 1989Google Scholar
  10. [10]
    R. A Jacobs “Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks”, COINS Tech. Rep. 90-27, March 1990Google Scholar
  11. [11]
    F. Kimura, M. Shridhar. “Handwritten numerical recognition based on multiple algorithms”, Pattern Recognition, V24 N10 pp969–983, 1991Google Scholar
  12. [12]
    S. Knerr, L. Personnaz, G. Dreyfus, “A New Approach To The Design Of Neural Networks Classifiers and its Applic. to the Aut Recog. of Handwriten Digits”, Adv.Neur.Inf. 3, Morgan Kauffmann, 1991Google Scholar
  13. [13]
    N. Morgan, H. Bourlard, “Factoring Networks by a Statistical Method”, Neural Computation, 4, 835–838 (1992)Google Scholar
  14. [14]
    A. Papoulis, Probability, Random Variables and Stochastic Processes 3rd ed. McGraw-Hill, 1991Google Scholar
  15. [15]
    L. I. Perlovsky, M. M. McManus, “Maximum Likelihood Neural Networks for Sensor Fusion and Adaptive Classification”, Neural Networks, V4 pp89–102, 1991Google Scholar
  16. [16]
    L. Xu, A. Krzyzak, C. Y. Suen, “Associative Switch For Combining Multiple Classifiers”, IEEE, 1991Google Scholar
  17. [17]
    L. Xu, A. Kryzak, C. Y. Suen, “Methods of Combining Multiple Classifiers and Their Applications to Handwritten Recognition”, IEEE T Systems, Man and Cybernetics, V22 N3, 1992Google Scholar
  18. [18]
    E. A. Wan, “Neural Networks Classification: A Bayesian Interpretation”. IEEE T. Neural Networks, V1 N4 Dec. 1990Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Alberto Ruiz García
    • 1
  • Francisco J. Arcas Túnez
    • 1
  1. 1.Departamento de Informática y Sistemas Facultad de InformáticaUniversidad de MurciaSpain

Personalised recommendations