Advertisement

Symbol Grounding in Connectionist and Adaptive Agent Models

  • Angelo Cangelosi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3526)

Abstract

This paper presents the Cognitive Symbol Grounding framework for modeling language in neural networks and adaptive agent simulations. This approach is characterized by the hypothesis that symbols are directly grounded into the agents’ own categorical representations, whilst at the same time having syntactic relationships with other symbols. The mechanism of grounding transfer is also introduced. This is the process by which the grounding of basic words, acquired via direct sensorimotor experience, is transferred to higher-order words via linguistic descriptions. Various simulations are briefly reviewed to demonstrate the use of the Cognitive Symbol Grounding approach.

Keywords

Categorical Perception Basic Word Linguistic Description Connectionist Approach Robotic Agent 
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.
    Cangelosi, A.: Grounding symbols in perceptual and sensorimotor categories: Connectionist and embodied approaches. In: Cohen, H., Lefebvre, C. (eds.) Handbook of Categorization in Cognitive Science. Elsevier, Amsterdam (2005)Google Scholar
  2. 2.
    Cangelosi, A., Harnad, S.: The Adaptive Advantage of Symbolic Theft over Sensorimotor Toil: Grounding Language in Perceptual Categories. Evolution of Communication 4, 117–142 (2000)CrossRefGoogle Scholar
  3. 3.
    Cangelosi, A., Parisi, D.: The processing of verbs and nouns in neural networks: Insights from synthetic brain imaging. Brain and Language 89, 401–408 (2004)CrossRefGoogle Scholar
  4. 4.
    Cangelosi, A., Riga, T.: Adaptive agent and robotic approaches to the sensorimotor ground-ing of language Artificial Intelligence Journal (in submission)Google Scholar
  5. 5.
    Coventry, K.R., Cangelosi, A., Rajapakse, R., Bacon, A., Newstead, S., Joyce, D., Richards, L.V.: Spatial prepositions and vague quantifiers: Implementing the functional geometric framework. In: Spatial Cognition Conference, Germany, October, 11–13 (2004)Google Scholar
  6. 6.
    Harnad, S.: The Symbol Grounding Problem. Physica D 42, 335–346 (1990)CrossRefGoogle Scholar
  7. 7.
    Harnad, S., Hanson, S.J., Lubin, J.: Categorical perception and the evolution of super-vised learning in neural nets. In: Powers, D.W., Reeker, L. (eds.) Proceedings of Proceedings of the AAAI Spring Symposium on Machine Learning of Natural Language and Ontology (1991)Google Scholar
  8. 8.
    Plunkett, K., Sinha, C., Møller, M.F., Strandsby, O.: Symbol grounding or the emergence of symbols? Vocabulary growth in children and a connectionist net. Connection Science 4, 293–312 (1992)CrossRefGoogle Scholar
  9. 9.
    Riga, T., Cangelosi, A., Greco, A.: Symbol grounding transfer with hybrid self-organizing/supervised neural networks. In: Proceedings of IJCNN 2004 International Joint Conference on Neural Networks, Budapest (July 2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Angelo Cangelosi
    • 1
  1. 1.Adaptive Behaviour and Cognition Research Group, School of Computing, Communications and ElectronicsUniversity of PlymouthUK

Personalised recommendations