A Feature Selection Approach for Emulating the Structure of Mental Representations

  • Marko Tscherepanow
  • Marco Kortkamp
  • Sina Kühnel
  • Jonathan Helbach
  • Christoph Schütz
  • Thomas Schack
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7064)


In order to develop artificial agents operating in complex ever-changing environments, advanced technical memory systems are required. At this juncture, two central questions are which information needs to be stored and how it is represented. On the other hand, cognitive psychology provides methods to measure the structure of mental representations in humans. But the nature and the characteristics of the underlying representations are largely unknown. We propose to use feature selection methods to determine adequate technical features for approximating the structure of mental representations found in humans. Although this approach does not allow for drawing conclusions transferable to humans, it constitutes an excellent basis for creating technical equivalents of mental representations.


Feature selection Mental representations Memory 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kawamura, K., Gordon, S.M., Ratanaswasd, P., Erdemir, E., Hall, J.F.: Implementation of cognitive control for a humanoid robot. International Journal of Humanoid Robotics 5(4), 547–586 (2008)CrossRefGoogle Scholar
  2. 2.
    Ben Amor, H., Ikemoto, S., Minato, T., Jung, B., Ishiguro, H.: A Neural Framework for Robot Motor Learning Based on Memory Consolidation. In: Beliczynski, B., Dzielinski, A., Iwanowski, M., Ribeiro, B. (eds.) ICANNGA 2007. LNCS, vol. 4432, pp. 641–648. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Chartier, S., Giguère, G., Langlois, D.: A new bidirectional heteroassociative memory encompassing correlational, competitive and topological properties. Neural Networks 22(5-6), 568–578 (2009)CrossRefGoogle Scholar
  4. 4.
    Goldstone, R.L., Kersten, A.: Concepts and categorization. In: Healy, A.F., Proctor, R.W. (eds.) Handbook of Psychology, vol. 4: Experimental Psychology, pp. 599–621. John Wiley & Sons, Hoboken (2003)Google Scholar
  5. 5.
    Edelman, S., Intrator, N.: Learning as extraction of low-dimensional representations. In: Goldstone, R.L., Schyns, P.G., Medin, D.L. (eds.) Perceptual Learning, pp. 353–380. Academic Press, San Diego (1997)CrossRefGoogle Scholar
  6. 6.
    Johansen, M.K., Kruschke, J.K.: Category representation for classification and feature inference. Journal of Experimental Psychology 31(6), 1433–1458 (2005)Google Scholar
  7. 7.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision 42(3), 145–175 (2001)CrossRefzbMATHGoogle Scholar
  8. 8.
    Lander, H.J., Lange, K.: Untersuchungen zur Struktur- und Dimensionsanalyse begrifflich repräsentierten Wissens. Zeitschrift für Psychologie 204, 55–74 (1996)Google Scholar
  9. 9.
    Bläsing, B., Tenenbaum, G., Schack, T.: The cognitive structure of movements in classical dance. Psychology of Sport and Exercise 10, 350–360 (2009)CrossRefGoogle Scholar
  10. 10.
    Schack, T., Mechsner, F.: Representation of motor skills in human long-term memory. Neuroscience Letters 391, 77–81 (2006)CrossRefGoogle Scholar
  11. 11.
    Hall, M.A.: Correlation-based Feature Selection for Machine Learning. Ph.D. thesis, Department of Computer Science, The University of Waikato, Hamilton, New Zealand (1999)Google Scholar
  12. 12.
    Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, New York (2001)CrossRefGoogle Scholar
  13. 13.
    Peng, H., Long, F., Ding, C.: Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(8), 1226–1238 (2005)CrossRefGoogle Scholar
  14. 14.
    Yu, L., Chen, H., Wang, S., Lai, K.K.: Evolving least squares support vector machines for stock market trend mining. IEEE Transactions on Evolutionary Computation 13(1), 87–102 (2009)CrossRefGoogle Scholar
  15. 15.
    Kononenko, I., Šikonja, M.R.: Non-myopic feature quality evaluation with (R)ReliefF. In: Liu, H., Motoda, H. (eds.) Computational Methods of Feature Selection, pp. 169–191. Chapman and Hall, Boca Raton (2008)Google Scholar
  16. 16.
    Schölkopf, B., Smola, A.J., Williamson, R.C., Bartlett, P.L.: New support vector algorithms. Neural Computation 12, 1207–1245 (2000)CrossRefGoogle Scholar
  17. 17.
    Fogel, D.B.: Evolutionary Computation, 3rd edn. IEEE Press, Piscataway (2006)zbMATHGoogle Scholar
  18. 18.
    Engelbrecht, A.P.: Computational Intelligence, 2nd edn. John Wiley & Sons, Hoboken (2007)CrossRefGoogle Scholar
  19. 19.
    Swain, M.J., Ballard, D.H.: Color indexing. International Journal of Computer Vision 7(1), 11–32 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Marko Tscherepanow
    • 1
    • 4
  • Marco Kortkamp
    • 1
  • Sina Kühnel
    • 2
    • 4
  • Jonathan Helbach
    • 1
  • Christoph Schütz
    • 3
    • 4
  • Thomas Schack
    • 3
    • 4
  1. 1.Applied Informatics, Faculty of TechnologyCenter of Excellence Bielefeld UniversityBielefeldGermany
  2. 2.Physiological Psychology, Faculty of Psychology and Sport SciencesCenter of Excellence Bielefeld UniversityBielefeldGermany
  3. 3.Neurocognition and Action, Faculty of Psychology and Sport SciencesCenter of Excellence Bielefeld UniversityBielefeldGermany
  4. 4.CITEC, Cognitive Interaction TechnologyCenter of Excellence Bielefeld UniversityBielefeldGermany

Personalised recommendations