Auto-associative memory by universal learning networks (ULNs)

In this paper, we propose a new auto correlation associative memory using universal learning networks (ULNs). The main purpose of this paper is to realize associative memory by training the network. Although so many useful models have been devised, there are some problems related to associative memory, such as the limitation of storage capacity or too small attractors of stored memories. To solve these problems, we obtain memory network by training network parameters not by calculating them in the conventional methods. Furthermore, we introduce "don't care nodes" into the networks just to enlarge network size and give more flexibility. We could verify that this method improves the memory capacity by computer simulations.