Abstract
We propose a novel approach to neuron-like models that consists in simulating cortical columns, i.e. associations of elementary neurons having a specific, functionnal activity. This model is built according to a theory which is consistent with neurobiological data. It provides autonomous units, each computing its output as a function of its inputs, modulated by such internal features as learning coefficients.
Implementing this model is achieved through a network of columns that simulates the inherently parallel functionning of the nervous system. Since each column behaves autonomously, the network is functionnaly specified by just describing the connectivity pattern of each area.
We describe in details this model and present the experimental conditions in which it has been and is now tested. Results already obtained show the efficiency of the model in terms of recognition raté as well as its ability to deal with higher level problems. We shall also discuss main general points such as topology, connectivity, temporal processing, etc.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Y. Burnod, “An adaptive neural network: The cerebral cortex”, Masson, Paris, 1988.
D.H. Ballard, “Cortical connections and parallel processing: Structure and function”, The behavioral and brain sciences 9, 67–120, 1986.
Y. Burnod, This volume.
C.D. Gilbert, T.N. Wiesel, “Laminar specialization and intra-corticai connections in cat primary visual cortex”, In the organization of the cerebral cortex, F. Schmitt et al eds., Cambridge, Mass., MIT Press, 1981.
P. Anizan, “Modèle à regulations hiérarchisées”, 3èmes Journées Neurosciences, Univ. Abc-Marseille I-II, 1986.
F. Fogelman Soulie, P. Gailinari, Y. Le Cun, S. Thiria. “Network learning”, Machine learning, vol 3, Y. Kodratoff, R. Michaiski Eds.
F. Guyot, F. Alexandre, J.P. Haton, Y. Burnod, “The Cortical Column, a New Processing Unit for Cortex-Like Networks”, Proc. CEC Workshop “From the Pixels to the Features”, Elsevier, 1989.
B. Delgutte, “Codage de la Parole Dans le Nerf Auditif”, Thèse, Université Paris VI, 1984.
E. I. Knudsen, S. du Lac, S. D. Esterly, “Computational Maps in the Brain”, Neurosciences, 10, p. 41–65, 1987.
J. Leboeuf, “Un Systeme Connexionniste Appliqué au Traitement Automatique de la Parole”, Thèse, Université de Paris-Sud, 1988.
F. Guyot, F. Alexandre, J.P. Haton, “Toward a Continuous model of the cortical column: application to speech recognition”, Proc. ICASSP-89, Glasgow, 1989.
T. Kohonen, “Self Organization and Associative Memory”, Springer, 1984.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guyot, F., Alexandre, F., Haton, J.P., Burnod, Y. (1990). A Potentially Powerful Connectionist Unit: The Cortical Column. In: Soulié, F.F., Hérault, J. (eds) Neurocomputing. NATO ASI Series, vol 68. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76153-9_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-76153-9_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76155-3
Online ISBN: 978-3-642-76153-9
eBook Packages: Springer Book Archive