Advertisement

Classification Based on Possibilistic Likelihood

  • Mathieu Serrurier
  • Henri Prade
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 299)

Abstract

Classification models usually associate one class for each new instance. This kind of prediction doesn’t reflect the uncertainty that is inherent in any machine learning algorithm. Probabilistic approaches rather focus on computing a probability distribution over the classes. However, making such a computation may be tricky and requires a large amount of data. In this paper, we propose a method based on the notion of possibilistic likelihood in order to learn a model that associates a possibility distribution over the classes to a new instance. Possibility distributions are here viewed as an upper bound of a family of probability distributions. This allows us to capture the epistemic uncertainty associated with the model in a faithful way. The model is based on a set of kernel functions and is obtained through an optimization process performed by a particle swarm algorithm. We experiment our method on benchmark dataset and compares it with a naive Bayes classifier.

Keywords

Particle Swarm Optimization Benchmark Dataset Epistemic Uncertainty Possibility Distribution Possibility Theory 
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.
    Benferhat, S., Tabia, K.: An Efficient Algorithm for Naive Possibilistic Classifiers with Uncertain Inputs. In: Greco, S., Lukasiewicz, T. (eds.) SUM 2008. LNCS (LNAI), vol. 5291, pp. 63–77. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  2. 2.
    Borgelt, C., Kruse, R.: Efficient maximum projection of database-induced multivariate possibility distributions. In: Proc. 7th IEEE Int. Conf. on Fuzzy Systems, pp. 663–668 (1998)Google Scholar
  3. 3.
    Cover, T.M., Hart, P.E.: Nearest neighbour pattern classification. IEEE Transactions on Information Theory 13, 21–27 (1967)CrossRefzbMATHGoogle Scholar
  4. 4.
    Dubois, D.: Possibility theory and statistical reasoning. Computational Statistics and Data Analysis 51, 47–69 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Dubois, D.: The Role of Epistemic Uncertainty in Risk Analysis. In: Deshpande, A., Hunter, A. (eds.) SUM 2010. LNCS, vol. 6379, pp. 11–15. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  6. 6.
    Dubois, D., Foulloy, L., Mauris, G., Prade, H.: Probability-possibility transformations, triangular fuzzy sets, and probabilistic inequalities. Reliable Computing 10, 273–297 (2004)MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Dubois, D., Prade, H.: When upper probabilities are possibility measures. Fuzzy Sets and Systems 49, 65–74 (1992)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Dubois, D., Prade, H.: On data summarization with fuzzy sets. In: Proc. of the 5th Inter. Fuzzy Systems Assoc. World Congress (IFSA 1993), Seoul, pp. 465–468 (1993)Google Scholar
  9. 9.
    Dubois, D., Prade, H., Sandri, S.: On possibility/probability transformations. In: Proceedings of Fourth IFSA Conference, pp. 103–112. Kluwer Academic Publ. (1993)Google Scholar
  10. 10.
    Jenhani, I., Ben Amor, N., Elouedi, Z.: Decision trees as possibilistic classifiers. Inter. J. of Approximate Reasoning 48(3), 784–807 (2008)CrossRefGoogle Scholar
  11. 11.
    Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of IEEE International Conference on Neural Networks, pp. 1942–1948 (1995)Google Scholar
  12. 12.
    Langley, P., Iba, W., Thompson, K.: An analysis of bayesian classifiers. In: Proceedings of AAAI 1992, vol. 7, pp. 223–228 (1992)Google Scholar
  13. 13.
    Mauris, G.: Inferring a possibility distribution from very few measurements. In: Soft Methods for Handling Variability and Imprecision. Advances in Soft Computing, vol. 48, pp. 92–99. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  14. 14.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmman, San Francisco (1988)Google Scholar
  15. 15.
    Serrurier, M., Prade, H.: Imprecise Regression Based on Possibilistic Likelihood. In: Benferhat, S., Grant, J. (eds.) SUM 2011. LNCS, vol. 6929, pp. 447–459. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  16. 16.
    Serrurier, M., Prade, H.: Maximum-likelihood principle for possibility distributions viewed as families of probabilities (regular paper). In: IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Taipei, Taiwan, pp. 2987–2993 (2011)Google Scholar
  17. 17.
    Zadeh, L.A.: Fuzzy sets as a basis for a theory of possibility. Fuzzy sets and systems 1, 3–25 (1978)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Mathieu Serrurier
    • 1
  • Henri Prade
    • 1
  1. 1.IRITUniversité Paul SabatierToulouse Cedex 9France

Personalised recommendations