Memory Properties of Non-Fully Interconnected Neural Network
Robert A. Kosiński, Andrzej Zagorski · Acta Physica Polonica A · 1994
A model of a neural network consisting of two states neurons witl tle number Ν of (symmetric) synaptic connections per neuron treated as a variable was investigated numerically.Hebb's rule was used for storing uncorrelated patterns in the network.Α maximal number of such patterns, which can be effectively retrieved by the network and tle process of deterioration of the memory, is examined as a function of tle number o[ synaptic connections per neuron.The influence of the number of neurons in tle network as well as boundary conditions for tle storage capacity of tle network are discussed.