Advertisement

Unsupervised Symbol Grounding and Cognitive Bootstrapping in Cognitive Vision

  • R. Bowden
  • L. Ellis
  • J. Kittler
  • M. Shevchenko
  • D. Windridge
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3617)

Abstract

In conventional computer vision systems symbol grounding is invariably established via supervised learning. We investigate unsupervised symbol grounding mechanisms that rely on perception action coupling. The mechanisms involve unsupervised clustering of observed actions and percepts. Their association gives rise to behaviours that emulate human action. The capability of the system is demonstrated on the problem of mimicking shape puzzle solving. It is argued that the same mechanisms support unsupervised cognitive bootstrapping in cognitive vision.

Keywords

Cognitive System Unsupervised Cluster Percept Space Inductive Logic Programming Action Vector 
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.

References

  1. 1.
    Granlund, G.: Organization of Architectures for Cognitive Vision Systems. In: Proceedings of Workshop on Cognitive Vision (2003)Google Scholar
  2. 2.
    Buccino, G., Binkofski, F., Riggio, L.: The mirror neuron system and action recognition. Brain and Language 89(2), 370–376 (2004)CrossRefGoogle Scholar
  3. 3.
    Siskind, J.M.: Reconstructing force-dynamic models from video sequences. Artificial Intelligence archive 151(1-2), 91–154 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Fitzpatrick, P., Metta, G., Natale, L., Rao, S., Sandini, G.: Learning About Objects Through Action: Initial Steps Towards Artificial Cognition. In: IEEE International Conference on Robotics and Automation (ICRA) (2003)Google Scholar
  5. 5.
    Magee, D., Needham, C.J., Santos, P., Cohn, A.G., Hogg, D.C.: Autonomous learning for a cognitive agent using continuous models and inductive logic programming from audio-visual input. In: Proc. AAAI Workshop on Anchoring Symbols to Sensor Data, pp. 17–24Google Scholar
  6. 6.
    Nock, R., Nielsen, F.: Statistical Region Merging. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(11), 1452–1458Google Scholar
  7. 7.
    Cordella, L., Foggia, P., Sansone, C., Vento, M.: An ecient algorithm for the inexact matching of arg graphs using a contextual transformational model. In: Proceedings of the International Conference on Pattern Recognition, vol. 3, pp. 180–184Google Scholar
  8. 8.
    Harnad, S.: The symbol grounding problem. Physica D 42, 335–346 (1990)CrossRefGoogle Scholar
  9. 9.
    Quine, W.V.O.: Word and Object. John Wiley and Sons, New York. MIT, Cambridge (1960)Google Scholar
  10. 10.
    Wittgenstein, L., Anscombe, G.E.M. (translator): Philosophical investigations: the German text with a revised English translation by Ludwig Wittgenstein. Blackwell, Oxford (2001) ISBN 0631231277Google Scholar
  11. 11.
    Marr, D.: Vision. Freeman, San Francisco (1982)Google Scholar
  12. 12.
    Gärdenfors, P.: How logic emerges from the dynamics of information. In: Van Eijck/Visser, Logic and Information Flow, pp. 49–77 (1994)Google Scholar
  13. 13.
    Granlund, G.: Organization of Architectures for Cognitive Vision Systems. In: Proceedings of Workshop on Cognitive Vision, Schloss Dagstuhl, Germany (2003)Google Scholar
  14. 14.
    Magee, D., Needham, C.J., Santos, P., Cohn, A.G., Hogg, D.C.: Autonomous learning for a cognitive agent using continuous models and inductive logic programming from audio-visual input. In: AAAI Workshop on Anchoring Symbols to Sensor Data (2004)Google Scholar
  15. 15.
    Chomsky, N.: Three models for the description of language. IRE Transactions on Information Theory 2, 113–124 (1956)CrossRefGoogle Scholar
  16. 16.
    Thrun, S.: Robotic Mapping: A Survey, Exploring Artificial Intelligence in the New Millennium. Morgan Kaufmann, San Francisco (2002)Google Scholar
  17. 17.
    McCarthy, J., Hayes, P.J.: Some Philosophical Problems from the Standpoint of Artificial Intelligence. In: Michie, D., Meltzer, B. (eds.) Machine Intelligence 4, pp. 463–502. Edinburgh University Press, Edinburgh (1969)Google Scholar
  18. 18.
    Granlund, G.H., Moe, A.: Unrestricted Recognition of 3D Objects for Robotics Using Multilevel Triplet Invariants. AI Magazine 25(2), 51–67 (2004)Google Scholar
  19. 19.
    Chella, A., Frixione, M., Gaglio, S.: A Cognitive Architecture for Artificial Vision. Artif. Intell. 89(1-2), 73–111 (1997)zbMATHCrossRefGoogle Scholar
  20. 20.
    Brooks, R.A.: Intelligence without Representation. Artificial Intelligence 47, 139–159 (1991)CrossRefGoogle Scholar
  21. 21.
    Johnson-Laird, P.N.: Mental Models. Harvard University Press, Cambridge (1983)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • R. Bowden
    • 1
  • L. Ellis
    • 1
  • J. Kittler
    • 1
  • M. Shevchenko
    • 1
  • D. Windridge
    • 1
  1. 1.Centre for Vision, Speech and Signal ProcessingThe University of SurreyGuildford, SurreyUK

Personalised recommendations