A scale-free neural network for modelling neurogenesis

• DOI: 10.1016/j.physa.2006.04.079
• Publication Date: 2006-05-20T11:22:30Z
• Authors: Juan I. Perotti; Francisco A. Tamarit; Sergio A. Cannas
• Keywords: QC Physics; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

In this work we introduce a neural network model for associative memory based on a diluted Hopfield model, which grows through a neurogenesis algorithm that guarantees that the final network is a small-world and scale-free one. We also analyze the storage capacity of the network and prove that its performance is larger than that measured in a randomly dilute network with the same connectivity.