NEURAL NETWORKS - ITERATIVE UNLEARNING ALGORITHM CONVERGING TO THE PROJECTOR RULE MATRIX

Authors
PLAKHOV AY SEMENOV SA
Citation
Ay. Plakhov et Sa. Semenov, NEURAL NETWORKS - ITERATIVE UNLEARNING ALGORITHM CONVERGING TO THE PROJECTOR RULE MATRIX, Journal de physique. I, 4(2), 1994, pp. 253-260
Citations number
22
Categorie Soggetti
Physics
Journal title
Journal de physique. I → ACNP
ISSN journal
11554304
Volume
4
Issue
2
Year of publication
1994
Pages
253 - 260
Database
ISI
SICI code
1155-4304(1994)4:2<253:NN-IUA>2.0.ZU;2-3
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.