An improved multidirectional associative memory

It is pointed out that multidirectional associative memories (MAMs) based on Kosko´s learning algorithm have some limitations such as low network capacity, difficulty in recalling from all the layers, and O(N²) weight matrices required for N -way patterns. The authors propose two improved MAM architectures. In the first architecture, high-order neurons are used to improve the network capacity. In the second architecture, which is based on a counter-propagation network, full network capacity is achieved with less training time and with the number of weight matrices growing with order O(N). The noise performance of these networks is also superior to that of a MAM model based on Kosko´s learning algorithm