On the storage of correlated patterns in Hopfield's model

The effects of storing p statistically independent but effectively correlated patterns in the Hopfield model of associative memory are studied. This leads us to propose a local learning rule which by enhancing the differences among the pattern allows the network to store them with an efficiency comparable to nonlocal learning rules On etudie les effets de stockage de p patterns statistiquement independants mais effectivement correles dans le modele de Hopfield de memoire associative. Ceci conduit a proposer une regle d'apprentissage locale qui, en augmentant les differences entre patterns, conduit a une memorisation d'efficacite comparable a celle des regles d'apprentissage non locales