Geodesic
Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold
Matematičeskoe modelirovanie, Tome 4 (1992) no. 10, pp. 101-110.

Voir la notice de l'article provenant de la source Math-Net.Ru

We analyse the mechanism by which Hopfield algorithm suppresses all patterns but one. We modify it by adapting the neuron response function and the threshold in each node to the global current pattern and to overall correlation among memory patterns. Such feedback lets the method recognize strongly correlated memories and operate on non-binary neurons (that is, those with more states than just 0,1). 
@article{MM_1992_4_10_a8,
     author = {B. M. Balter and I. V. Popova},
     title = {Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold},
     journal = {Matemati\v{c}eskoe modelirovanie},
     pages = {101--110},
     publisher = {mathdoc},
     volume = {4},
     number = {10},
     year = {1992},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MM_1992_4_10_a8/}
}
TY  - JOUR
AU  - B. M. Balter
AU  - I. V. Popova
TI  - Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold
JO  - Matematičeskoe modelirovanie
PY  - 1992
SP  - 101
EP  - 110
VL  - 4
IS  - 10
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MM_1992_4_10_a8/
LA  - ru
ID  - MM_1992_4_10_a8
ER  - 
%0 Journal Article
%A B. M. Balter
%A I. V. Popova
%T Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold
%J Matematičeskoe modelirovanie
%D 1992
%P 101-110
%V 4
%N 10
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MM_1992_4_10_a8/
%G ru
%F MM_1992_4_10_a8
B. M. Balter; I. V. Popova. Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold. Matematičeskoe modelirovanie, Tome 4 (1992) no. 10, pp. 101-110. http://geodesic.mathdoc.fr/item/MM_1992_4_10_a8/