Recalling properties of non-random patterns in neural networks A Monte-Carlo study

We introduce a neural network with the ability of recalling p non-random patterns displaying a hierarchical distribution of activities for all p N − 1, N being the number of neurons. The stability of the retrieval states is studied as a function of temperature T and α = p/N. The temperature below which the patterns are retrievable states has been determined by computer simulations. The features of the memory stability are related to a weak correlation of the synaptic efficacy distribution.