Biological Cybernetics

, Volume 46, Issue 1, pp 27–39 | Cite as

Dynamic connections in neural networks

  • Jerome A. Feldman


Massively parallel (neural-like) networks are receiving increasing attention as a mechanism for expressing information processing models. By exploiting powerful primitive units and stability-preserving construction rules, various workers have been able to construct and test quite complex models, particularly in vision research. But all of the detailed technical work was concerned with the structure and behavior offixed networks. The purpose of this paper is to extend the methodology to cover several aspects of change and memory.


Neural Network Information Processing Complex Model Vision Research Technical Work 
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. Anderson, J.R., Bower, G.H.: Human associative memory. Washington, DC: V.H. Winston and Sons 1972Google Scholar
  2. Ballard, D.H.: Parameter networks. TR 75, Computer Science Dept., U. Rochester, 1981; Proc. 7th IJCAI, Vancouver, B.C., August 1981Google Scholar
  3. Barto, A.G., Sutton, R.S., Brouwer, P.S.: Associative search network: a reinforcement learning associative memory. Biol. Cybern.40, 201–211 (1981)Google Scholar
  4. Buser, P.A., Roguel-Buser, A. (eds): Cerebral correlates of conscious experience. Amsterdam: North-Holland 1978Google Scholar
  5. Cotman, C.W. (ed): Neuronal plasticity. New York: Raven Press 1978Google Scholar
  6. Dell, G.S., Reich, P.A.: Toward a unified model of slips of the tonguc. In: Errors in linguistic performance: slips of the tongue, car, pen, and hand. Fromkin, V.A. (ed) New York: Academic Press 1980Google Scholar
  7. Dev, P.: Perception of depth surfaces in random-dot stereograms: a neural model. Intl. J. Man-Machine Stud.7, 511–528 (1975)Google Scholar
  8. Doty, R.W.: Neurons and memory: some clues. In: Brain mechanisms in memory and learning: from the single neuron to man, Brazier, M.A.B. Int. J. Brain Research Organization Monograph Series, Vol. 4. New York: Raven Press 1979Google Scholar
  9. Fahlman, S.E.: The Hashnet interconnection scheme. Computer Science Dept. Carnegie-Mellon U., June 1980Google Scholar
  10. Feldman, J.A.: Four frames suffice. TR 99, Computer Science Dept., U. Rochester 1982Google Scholar
  11. Feldman, J.A.: A connectionist model of visual memory. In: Parallel models of associative memory. Hinton, G.E., Anderson, J.A. (eds.) Hillsdale, NJ: Lawrence Erlbaum Associates, Publishers 1981aGoogle Scholar
  12. Feldman, J.A.: Memory and change in connection networks. TR 96, Computer Science Dept., U. Rochester 1981bGoogle Scholar
  13. Feldman, J.A., Ballard, D.H.: Connectionist models and their properties. Cogn. Sci. 1982 (to appear)Google Scholar
  14. Feldman, J.A., Nigam, A.: A model and proof technique for message-based systems. SIAM J. Comput.9, 4 (1980)Google Scholar
  15. Grossberg, S.: Biological competition: decision rules, patterm formation, and oscillations. Proc. Natl. Acad. Sci. USA77, 4, 2238–2342 (1980)Google Scholar
  16. Hanson, A.R., Riseman, E.M. (eds): Computer vision systems. New York: Academic Press 1978Google Scholar
  17. Hinton, G.E., Anderson, J.A. (eds): Parallel models of associative memory. Hillsdale, NJ: Lawrence Erlbaum Associates, Publishers 1981Google Scholar
  18. Jusczyk, P.W., Klein, R.M. (eds): The nature of thought: essays in honour of D.O. Hebb. Hillsdale, NJ: Lawrence Erlbaum Associates, Publishers 1980Google Scholar
  19. Kandel, E.R.: The cellular basis of behavior. San Francisco, CA: Freeman 1976Google Scholar
  20. Marr, D.C.: Vision. San Francisco, CA: Freeman 1980Google Scholar
  21. Marr, D.C., Poggio, T.: Cooperative computation of stereo disparitly. Science194, 283–287 (1976)Google Scholar
  22. McClelland, J.L., Rumelhart, D.E.: An interactive activation model of the effect of context in perception. Part 1. Psych. Rev. (to appear)Google Scholar
  23. Minsky, M., Papert, S.: Perceptrons. Cambridge, MA: The MIT Press 1972Google Scholar
  24. Pippenger, N.: On rearrangeable and non-blocking switching networks. J. Comput. Syst. Sci.17, 2, October (1978)Google Scholar
  25. Posner, M.I.: Chronometric explorations of mind. Hillsdale, NJ: Lawrence Erlbaum Associates, Publishers 1978Google Scholar
  26. Richter, J., Ullman, S.: A model for the temporal organization ofX-andY-type receptive fields in the primate retina. Biol. Cybern.43, 127–145 (1982)Google Scholar
  27. Sabbah, D.: Design of a highly parallel visual recognition system. Proc. 7th IJCAI, Vancouver, B.C., August 1981Google Scholar
  28. Sleeman, D., Langley, P., Mitchell, T.M.: Learning from solution paths: an approach to the credit assignment problem. The AI Magazine, Spring 48–52 (1982)Google Scholar
  29. Stent, G.S.: A physiological mechanism for Hebb's postulate of learning. Proc. Natl. Acad. Sci. USA70, 4, 997–1001 (1973)Google Scholar
  30. Sutton, R.S., Barto, A.G.: Toward a modern theory of adaptive networks: expectation and prediction. Psychol. Rev.88, 2, 135–170 (1981)Google Scholar
  31. Torioka, T.: Pattern separability in a random neural net with inhibitory connections. Biol. Cybern.34, 53–62 (1979)Google Scholar
  32. Wickelgren, W.A.: Chunking and consolidation: a theoretical synthesis of semantic networks. configuring in conditioning,S-R versus cognitive learning, normal forgetting, the amnesic syndrome, and the hippocampal arousal system. Psychol. Rev.86, 44–60 (1979)Google Scholar

Copyright information

© Springer-Verlag 1982

Authors and Affiliations

  • Jerome A. Feldman
    • 1
  1. 1.Computer Science DepartmentUniversity of RochesterRochesterUSA

Personalised recommendations