Advertisement

Multi-layer Perceptron on Interval Data

  • Fabrice Rossi
  • Brieuc Conan-Guez
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)

Abstract

We study in this paper several methods that allow one to use interval data as inputs for Multi-layer Perceptrons. We show that interesting results can be obtained by using together two methods: the extremal values method which is based on a complete description of intervals, and the simulation method which is based on a probabilistic understanding of intervals. Both methods can be easily implemented on top of existing neural network software.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Beheshti, M., Berrached, A., De Korvin, A., Hu, C., and Sirisaengtaksin, O. (1998). On interval weighted three-layer neural networks. In Proceedings of the 31 Annual Simulation Symposium,pages 188–194. IEEE Computer Society Press.CrossRefGoogle Scholar
  2. Bishop, C. (1995a). Neural Networks for Pattern Recognition. Oxford Press.Google Scholar
  3. Bishop, C. (1995b). Training with noise is equivalent to Tikhonov regularization. Neural Computation, 7 (1): 108–116.CrossRefGoogle Scholar
  4. Bock, H.-H. and Diday, E., editors (2000). Analysis of Symbolic Data. Exploratory methods for extracting statistical information from complex data. Springer Verlag.Google Scholar
  5. Grandvalet, Y., Canu, S., and Boucheron, S. (1997). Noise injection: Theoretical prospects. Neural Computation, 9 (5): 1093–1108.CrossRefGoogle Scholar
  6. Moore, R. (1966). Interval Analysis. Englewood Cliffs, New Jersey.zbMATHGoogle Scholar
  7. Sietsma, J. and Dow, R. (1991). Creating articial neural networks that generalize. Neural Networks, 4 (1): 67–79.CrossRefGoogle Scholar
  8. Simoff, S. J. (1996). Handling uncertainty in neural networks: An interval approach. In Int. Conf. on Neural Networks, pages 606–610, Washington. IEEE.Google Scholar
  9. Sima, J. (1995). Neural Expert Systems. Neural Networks, 8 (2): 261–271.CrossRefGoogle Scholar
  10. Zell, A. et al. (1995). SNNS 4.1 user manual. University of Stuttgart.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Fabrice Rossi
    • 1
  • Brieuc Conan-Guez
    • 2
  1. 1.Place du Maréchal de Lattre de TassignyLISE/CEREMADE, UMR CNRS 7534, Université Paris-IX DauphineParisFrance
  2. 2.Domaine de Voluceau, RocquencourtINRIALe Chesnay CedexFrance

Personalised recommendations