Storing extensively many weighted patterns in a saturated neural network

Abstract
The performance of the Hopfield model of a neural network with extensively many weighted patterns is analysed. If the system size is N, then N patterns, each provided with a suitable weight, are stored. The weights may be associated with a temporal order and, if appropriately chosen, they allow a gradual fading out of the extensively many stored patterns. Particular emphasis is put on the underlying mathematical structure.

This publication has 17 references indexed in Scilit: