Learning from Incongruence

  • Tomáš Pajdla
  • Michal Havlena
  • Jan Heller
Part of the Studies in Computational Intelligence book series (SCI, volume 384)

Abstract

We present an approach to constructing a model of the universe for explaining observations and making decisions based on learning new concepts. We use a weak statistical model, e.g. a discriminative classifier, to distinguish errors in measurements from improper modeling. We use boolean logic to combine outcomes of direct detectors of relevant events, e.g. presence of sound and presence of human shape in the field of view, into more complex models explaining the states in which the universe may appear. The process of constructing a new concept is initiated when a significant disagreement - incongruence - has been observed between incoming data and the current model of the universe. Then, a new concept, i.e. a new direct detector, is trained on incongruent data and combined with existing models to remove the incongruence.We demonstrate the concept in an experiment with human audio-visual detection.

Keywords

Feature Vector Direct Detector Horn Clause Audio Event Walk Person 
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.
    Popper, K.R.: The Logic of Scientific Discovery. Routledge, New York (1995)Google Scholar
  2. 2.
    Pavel, M., Jimison, H., Weinshall, D., Zweig, A., Ohl, F., Hermansky, H.: Detection and identification of rare incongruent events in cognitive and engineering systems. Dirac white paper, OHSU (2008)Google Scholar
  3. 3.
    Weinshall, D., et al.: Beyond novelty detection: Incongruent events, when general and specific classifiers disagree. In: NIPS 2008, pp. 1745–1752 (2008)Google Scholar
  4. 4.
    Halmos, P.R.: Lectures on Boolean Algebras. Springer, Heidelberg (1974)MATHCrossRefGoogle Scholar
  5. 5.
    Franc, V., Sonneburg, S.: Optimized cutting plane algorithm for large-scale risk minimization. Journal of Machine Learning Research 10, 2157–2232 (2009)Google Scholar
  6. 6.
    Pajdla, T., Havlena, M., Heller, J., Kayser, H., Bach, J.H., Anemüller, J.: Incongruence detection for detecting, removing, and repairing incorrect functionality in low-level processing. Research Report CTU–CMP–2009–19, Center for Machine Perception, K13133 FEE Czech Technical University (2009)Google Scholar
  7. 7.
    Wikipedia: Horn Clause (2010), http://en.wikipedia.org/wiki/Horn_clause
  8. 8.
    Wikipedia: PROLOG (2010), http://en.wikipedia.org/wiki/Prolog

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Tomáš Pajdla
    • 1
  • Michal Havlena
    • 1
  • Jan Heller
    • 1
  1. 1.Center for Machine Perception, Department of Cybernetics, FEECTU in PraguePrague 6Czech Republic

Personalised recommendations