Neurobiological inspiration for the architecture and functioning of cooperating neural networks
In order to emulate more complex and more realistic human-like functions, it is now well admitted that a single monolithic neural network is not sufficient. Biological data show that the cortex is a set of interconnected neural networks. Beyond the classical view of one way feedforward neural network guiding an information flow from an input to an output layer, we now have to imagine architectures and functioning rules that permit cooperation and information exchange between such neural networks. Inspired with biological data, we propose here such a scheme bringing into play of complex units like the cortical column, a functional micro-circuit repeated throughout the cortex. This basic unit of treatment gathers the classical weighted sum for feedforward information flow and sigma-pi operations for cooperation between different axis of treatment. We illustrate this model with an application of cooperation between character recognition and localization.
Unable to display preview. Download preview PDF.
- Alexandre, F., Guyot, F., Haton, J.P. (1990) A connectionist network with two complementary visual processing systems for x-ray image interpretation, INNC'90, Paris.Google Scholar
- Alexandre, F., Burnod, Y., Guyot, F., Haton, J. P. (1991) The Cortical Column: a new processing unit for multilayered networks, Neural Networks,Vol 4, n 1, pp. 15–25.Google Scholar
- Alexandre, F., Guyot, F. (1992) A connectionist model constrained by an optical implementation, Int. Congress on Artificial Neural Networks, Brighton, Sept. 92.Google Scholar
- Alexandre, F., Guyot, F. (1994) Evaluation d'un modèle connexionniste simple pour la reconnaissance automatique de caractères, Colloque National sur l'Ecrit et le Document, Rouen, Juillet 1994.Google Scholar
- Burnod, Y. (1988) An adaptive neural network: The cerebral cortex, 2nd Edition, Masson, Paris.Google Scholar
- Burnod, Y, Grandguillaume, P., Otto, I., Ferraina, S., Johnson, P., Caminiti, R. (1992) Visuomotor Transformations Underlying Arm Movements toward Visual Targets: A Neural Network Model of Cerebral Cortical Operations, Journ. of Neuroscience, 12, 4, 1435–1453.Google Scholar
- Guigon, E. (1993) Modélisation des propriétés du cortex cérébral, PhD Thesis, Ecole centrale de ParisGoogle Scholar
- Guyot, F., Alexandre, F., Haton, J.P. (1990a) Principles and applications of the cortical column symbolic neural model, IJCNN'90, San Diego.Google Scholar
- Guyot, F., Alexandre, F., Dingeon, C., Haton, J.P. (1990b) The Cortical Column as a Model for Speech Recognition: Principles and First Experiments, in Speech Recognition and Understanding Recent Advances, Trends and Applications, Springer Verlag.Google Scholar
- [LeCun, Y.,]Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., Jackel, L. (1990) Handwritten Digit Recognition with Back-propagation Network, NIPS, vol.2, Morgan Kaufmann.Google Scholar
- O'Regan, J. K. (1990) Les “vrais” mystères de la vision, 5èmes journées NSI, Aussois.Google Scholar
- Pican, N., Alexandre, F. (1993) Integration of Context in Process Models used for Neuro-Control. Proc. IEEE Systems Man and Cybernetics, Le Touquet.Google Scholar
- Rumelhart, D., Mc Clelland, J. (1986) Parallel distributed processing, MIT Press, Cambridge.Google Scholar