Share Email Print
cover

Proceedings Paper

Rank-based Hebbian learning in a multilayered neural network
Author(s): James M. Vaccaro; D. Gourion; Manuel Samuelides; S. Thorpe
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Recent work on biologically motivated networks have shown that the visual system can process a natural scene more quickly by encoding the order of neural firing rather than the frequency of firing. This `order of firing' encoding scheme has led to a rank-based approach which converts activation energy into a time-dependent pulse code. This paper focuses towards the contribution of unsupervised learning to the training of integrate and fire neurons within multi-layer networks. First, we propose an unsupervised learning algorithm and we test it on a simple recognition task. Then, we propose a multilayer architecture of integrate and fire neurons to solve a more complex vision task. This architecture is efficiently trained by an algorithm combining supervised and unsupervised rank-based hebbian learning. Further improvements are proposed in the final discussion.

Paper Details

Date Published: 22 March 1999
PDF: 15 pages
Proc. SPIE 3728, Ninth Workshop on Virtual Intelligence/Dynamic Neural Networks, (22 March 1999); doi: 10.1117/12.343048
Show Author Affiliations
James M. Vaccaro, ONERA (France), Air Force Research Lab. (USA), and Univ. of California/San Diego (United States)
D. Gourion, ONERA (France)
Manuel Samuelides, ONERA (France) and Ecole Nationale Superieure de l'Aeronautique et de l'Espace (France)
S. Thorpe, CNRS Ctr. de Recherche Cerveau et Cognition (France)


Published in SPIE Proceedings Vol. 3728:
Ninth Workshop on Virtual Intelligence/Dynamic Neural Networks
Thomas Lindblad; Mary Lou Padgett; Jason M. Kinser, Editor(s)

© SPIE. Terms of Use
Back to Top