Neural Processing Letters

, Volume 11, Issue 1, pp 17–27 | Cite as

Learning Synaptic Clusters for Nonlinear Dendritic Processing

  • Michael W. Spratling
  • Gillian M. Hayes


Nonlinear dendritic processing appears to be a feature of biological neuronsand would also be of use in many applications of artificial neuralnetworks. This paper presents a model of an initially standard linearnode which uses unsupervised learning to find clusters of inputs withinwhich inactivity at one synapse can occlude the activity at the othersynapses.

dendritic processing higher-order neurons invariance unsupervised learning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Anderson, R. A., Essich, G. K. and Siegal, R. M.: Encoding of spatial location by posterior parietal neurons, Science 230 (1985), 456-458.Google Scholar
  2. 2.
    Tovee, M. J., Rolls, E. T. and Azzopardi, P.: Translation invariance in the responses to faces of single neurons in the temporal visual cortical areas of the alert macaque, Journal of Neurophysiology 72(3) (1994), 1049-1060.Google Scholar
  3. 3.
    Mel, B.W.: Information processing in dendritic trees, Neural Computation 6 (1994), 1031-1085.Google Scholar
  4. 4.
    Feldman, J. A. and Ballard, D. H.: Connectionist models and their properties, Cognitive Science 6 (1982), 205-254.Google Scholar
  5. 5.
    Mel, B. W.: The sigma-pi column: A model of associative learning in cerebral cortex, Technical Report CNS Memo 6, Computation and Neural Systems Program, California Institute of Technology, 1990.Google Scholar
  6. 6.
    Rumelhart, D. E., McClelland, J. L. and The PDP Research Group (eds.), Parallel Distributed Processing: Explorations in the Microstructures of Cognition. Volume I: Foundations, MIT Press, Cambridge, MA, 1986.Google Scholar
  7. 7.
    Mel, B. W. and Koch, C.: Sigma-pi learning: On radial basis functions and cortical associative learning, In: D. S. Touretzsky (ed.), Advances in Neural Information Processing Systems 2, Morgan Kaufmann, San Mateo, CA, 1990, pp. 474-481.Google Scholar
  8. 8.
    Durbin, R. and Rumelhart, D. E.: Product units: A computationally powerful and biologically plausible extention to backpropagation networks, Neural Computation 1 (1990), 133-142.Google Scholar
  9. 9.
    Mel, B. W.: The clusteron: Toward a simple abstraction for a complex neuron, In: J. E. Moody, S. J. Hanson and R. P. Lippmann (eds.), Advances in Neural Information Processing Systems 4, Morgan Kauffmann, San Mateo, CA, 1992.Google Scholar
  10. 10.
    Földiák, P.: Learning invariance from transformation sequences, Neural Computation 3 (1991), 194-200.Google Scholar
  11. 11.
    Becker, S.: Learning to categorize objects using temporal coherence, In: S. J. Hanson, J. D. Cowan and C. L. Giles (eds.), Advances in Neural Information Processing Systems 5, Morgan Kaufmann, San Mateo, CA, 1993, pp. 361-368.Google Scholar

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Michael W. Spratling
    • 1
  • Gillian M. Hayes
    • 1
  1. 1.Department of Artificial IntelligenceUniversity of EdinburghEdinburghU.K.

Personalised recommendations