| Numéro |
J. Phys. I France
Volume 4, Numéro 2, February 1994
|
|
|---|---|---|
| Page(s) | 253 - 260 | |
| DOI | https://doi.org/10.1051/jp1:1994105 | |
DOI: 10.1051/jp1:1994105
J. Phys. I France 4 (1994) 253-260
Institute of Physics and Technology, Prechistenka Str. 13/7, Moscow 119034, Russia
© Les Editions de Physique 1994
J. Phys. I France 4 (1994) 253-260
Neural networks : iterative unlearning algorithm converging to the projector rule matrix
A. Yu. Plakhov and S. A. SemenovInstitute of Physics and Technology, Prechistenka Str. 13/7, Moscow 119034, Russia
(Received 31 March 1993, received in final form 4 October 1993, accepted 12 October 1993)
Abstract
The iterative unlearning algorithm for connectivity self-correction
is proposed. No presentation of patterns during the iteration process
is required. Starting from the Hebbian connectivity, the convergence
of the (rescaled) iterated connection matrix to the projector rule
one is proven, for arbitrary set of p < N binary patterns.
© Les Editions de Physique 1994