Extension of HUMANN for Dealing with Noise and with Classes of Different Shape and Size: A Parametric Study

  • Patricio García Báez
  • Carmen Paz Suárez Araujo
  • Pablo Fernández López
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2085)


In this paper an extension of HUMANN (hierarchical unsupervised modular adaptive neural network) is presented together with a parametric study of this network in dealing with noise and with classes of any shape and size. The study has been made based on the two most noise dependent HUMANN parameters, λ and μ, using synthesised databases (bidimensional patterns with outliers and classes with different probability density distribution). In order to evaluate the robustness of HUMANN a Monte Carlo [1] analysis was carried out using the creation of separate data in given classes. The influence of the different parameters in the recovery of these classes was then studied.


Success Ratio Probability Density Distribution Outlier Data Tolerance Module Silent Synapse 
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.
    Afzal Upal, M.: Monte Carlo Comparison of Non-Hierarchical Unsupervised Classifiers. Master’s thesis, University Of Saskatchewan (1995).Google Scholar
  2. 2.
    Makhoul, J., Roucos, S., Gish, H.: Vector quantization in speech coding. In: Proceedings of the IEEE, Vol. 73,Num. 11 (1985) 1551–1588.CrossRefGoogle Scholar
  3. 3.
    Anderberg, M.R.: Cluster Analysis for Applications. Academic Press, New York (1973).zbMATHGoogle Scholar
  4. 4.
    Cheesemann, P., Kelly, J., Self, M., Sutz, J., Taylor, W., Freeman, D.: Autoclass: A Bayesian clasification sustem. In: Proceedings of the Fifth International Conference on Machine Learning, San Mateo, CA (1988) 54–64.Google Scholar
  5. 5.
    Wallacem C.S., Dowe, D.L.: Intrinsic classification by MML-the Snob program. In: Proceedings of the Seventh Australian Joint Conferencie on Artificial Intelligence, Singapore (1994) 37–44.Google Scholar
  6. 6.
    Kohonen, T.: The Self-Organizing Map. In: Proceedings of IEEE, Special Issue on Neural Networks, Vol. 78,Num. 9 (1990) 1464–1480.Google Scholar
  7. 7.
    Carpenter, G.A., Grossberg, S.: ART 2: Self-Organization of Stable Category Recognition Codes for Analog Input Patterns. In: Applied Optics, Vol. 26 (1987) 4919–4930.CrossRefGoogle Scholar
  8. 8.
    Thomopoulos, S.C.A., Bougoulias, D.K., Wann, C.D.: Dignet: An Unsupervised Learning Algorithm for Clustering and Data Fusion. In: IEEE Transactions on Aerospace and Electronic Systems, Vol. AES-31,Num. 1 (1995) 21–38.CrossRefGoogle Scholar
  9. 9.
    García, P., Fernández, P., Suárez, C.P.: A Parametric Study of Humann in relation to the Noise. Application to the Identification of Compounds of Environmental Interest. In: Systems Analysis Modelling Simulation, in press.Google Scholar
  10. 10.
    García, P., Suárez, C.P., Rodríguez, J., Rodríguez, M.: Unsupervised Classification of Neural Spikes With a Hybrid Multilayer Artificial Neural Network. In: Journal of Neuroscience Methods, Vol. 82 (1998) 59–73.CrossRefGoogle Scholar
  11. 11.
    Kohonen, T.: Self-Organizing Maps, 2nd ed.. Springer Series in Information Sciences, Vol. 30. Springer-Verlag, Berlin Heidelberg New York (1997).zbMATHGoogle Scholar
  12. 12.
    Atwood, H.L., Wojtowicz, J.M.: Silent Synapses in Neural Plasticity: Current Evidence. In: Learning & Memory, Vol. 6 (1999) 542–571.CrossRefGoogle Scholar
  13. 13.
    Afzal Upal, M., Neufeld, E.M.: Comparison of Unsupervised Classifiers. In: Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, San Mateo, CA (1989) 781–787.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Patricio García Báez
    • 1
  • Carmen Paz Suárez Araujo
    • 2
  • Pablo Fernández López
    • 2
  1. 1.Department of Statistics, Operating Research and ComputationUniversity of La LagunaCanary IslandsSpain
  2. 2.Department of Computer Sciences and SystemsUniversity of Las Palmas de Gran CanariaCanary IslandsSpain

Personalised recommendations