Postprint version. Published in Neural Networks, Volume 11, Issue 5, July 1, 1998, pages 869-876.
NOTE: At the time of publication, the author Franz Kurfess was affiliated with the New Jersey Institute of Technology. Currently, August 2008, he is Professor of Computer Science at California Polytechnic State University - San Luis Obispo .
The definitive version is available at https://doi.org/10.1016/S0893-6080(98)00035-5.
In this paper, the memory capacity of incompletely connected associative memories is investigated. First, the capacity is derived for memories with fixed parameters. Optimization of the parameters yields a maximum capacity between 0.53 and 0.69 for hetero-association and half of it for auto-association improving previously reported results. The maximum capacity grows with increasing connectivity of the memory and requires sparse input and output patterns. Further, parameters can be chosen in such a way that the information content per pattern asymptotically approaches 1 with growing size of the memory.