Layered Hybrid Connectionist Models for Cognitive Science

  • Jerome Feldman
  • David Bailey
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1778)


Direct connnectionist modeling of higher cognitive functions, such as language understanding, is impractical. This chapter describes a principled multi-layer architecture that supports AI style computational modeling while preserving the biological plausibility of structured connectionist models. As an example, the connectionist realization of Bayesian model merging as recruitment learning is presented.


Connectionist Model Word Sense Computational Level Triangle Unit Concept Unit 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bailey, D.R.: When Push Comes to Shove: A Computational Model of the Role of Motor Control in the Acquisition of Action Verbs. PhD thesis, Computer Science Division, EECS Department, University of California at Berkeley (1997)Google Scholar
  2. 2.
    Bailey, D.R., Feldman, J.A., Narayanan, S., Lakoff, G.: Modeling embodied lexical development. In: Proceedings of the 19th Cognitive Science Society Conference, pp. 19–24 (1997)Google Scholar
  3. 3.
    Damasio, A.R., Tranel, D.: Nouns and verbs are retrieved with differently distributed neural systems. Proceedings of the National Academy of Sciences 90, 4757–4760 (1993)CrossRefGoogle Scholar
  4. 4.
    Diederich, J.: Knowledge-intensive recruitment learning. Technical Report TR-88-010, International Computer Science Institute, Berkeley, CA (1988)Google Scholar
  5. 5.
    Feldman, J.A.: Dynamic connections in neural networks. Biological Cybernetics 46, 27–39 (1982)CrossRefGoogle Scholar
  6. 6.
    Feldman, J.A., Ballard, D.: Connectionist models and their properties. Cognitive Science 6, 205–254 (1982)CrossRefGoogle Scholar
  7. 7.
    Grannes, D.J., Shastri, L., Narayanan, S., Feldman, J.A.: A connectionist encoding of schemas and reactive plans. In: Poster presented at 19th Cognitive Science Society Conference (1997)Google Scholar
  8. 8.
    Hebb, D.O.: The Organization of Behavior. Wiley, New York (1949)Google Scholar
  9. 9.
    Hummel, J.E., Biederman, I.: Dynamic binding in a neural network for shape recognition. Psychological Review 99, 480–517 (1992)CrossRefGoogle Scholar
  10. 10.
    Lynch, G., Granger, R.: Variations in synaptic plasticity and types of memory in corticohippocampal networks. Journal of Cognitive Neuroscience 4(3), 189–199 (1992)CrossRefGoogle Scholar
  11. 11.
    Shastri, L.: Semantic Networks: An evidential formalization and its connectionist realization. Morgan Kaufmann, Los Altos (1988)MATHGoogle Scholar
  12. 12.
    Shastri, L.: A model of rapid memory formation in the hippocampal system. In: Proceedings of the 19th Cognitive Science Society Conference, pp. 680–685 (1997)Google Scholar
  13. 13.
    Ajjanagadde, V., Shastri, L.: Rules and variables in neural nets. Neural Computation 3, 121–134 (1991)CrossRefGoogle Scholar
  14. 14.
    Stolcke, A., Omohundro, S.: Best-first model merging for hidden Markov model induction. Technical Report TR-94-003, International Computer Science Institute, Berkeley, CA (January 1994)Google Scholar
  15. 15.
    Sun, R.: On variable binding in connectionist networks. Connection Science 4, 93–124 (1992)CrossRefGoogle Scholar
  16. 16.
    Valiant, L.: Circuits of the mind. Oxford University Press, New York (1994)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Jerome Feldman
    • 1
  • David Bailey
    • 1
  1. 1.International Computer Science InstituteBerkeleyUSA

Personalised recommendations