Performance of associative memory using partially-connected networks

From both a neurobiological viewpoint and an implementation perspective, the neuron network is partially-connected. In this paper, we show that associative memory networks with complex topology. Owing to the partial connection in delta distribute network, the associative memory has feature of higher storage capacity, but the basin of attraction is shrunk. The comparison of the performance among the ER network, Small-world network and delta distribute network investigates that associative memory network¿s performance does not simply depend on the mean degree of the neurons, but also on the structure of the connectivity. The simulation shows that the delta distribute network performance the most efficient performance.