Hopfield-like neural network.
Husek D. Frolov · 1995
Informational and dynamic properties of sparsely encoded Hopfield-like neural network performing the functions of autoassociative memory are investigated ana- lytically and by computer simulation. It is shown that the informational capacity and the processing rate monotonically increase if the sparseness increases.In contra- diction to this, the size of the attraction basins and the recall quality initially change nonmonotonically. An optimal sparseness exists when the information extracteed from the network due to correction of destroyed stored patterns are maximal.