The three-state layered neural network with finite dilution

Abstract

The dynamics and the stationary states of an exactly solvable three-state layered feed-forward neural network model with asymmetric synaptic connections, finite dilution and low pattern activity are studied in extension of a recent work on a recurrent network. Detailed phase diagrams are obtained for the stationary states and for the time evolution of the retrieval overlap with a single pattern. It is shown that the network develops instabilities for low thresholds and that there is a gradual improvement in network performance with increasing threshold up to an optimal stage. The robustness to synaptic noise is checked and the effects of dilution and of variable threshold on the information content of the network are also established.Comment: Latex, 11 pages, 6 figure

Synchronous versus sequential updating in the three-state Ising neural network with variable dilution

“…The results for the extremely diluted architecture appeared in [13] and have been extended later to the whole dilution range in [14]. The layered architecture with variable dilution has been examined recently [15]. Nothing has been reported on the equilibrium properties for the recurrent architectures, however, when synchronous updating is used.…”