Generalized Connectionist Associative Memory

This paper presents a generalized associative memory model, which stores a collection of tu-ples whose components are sets rather than scalars. It is shown that all library patterns are stored stably. On the other hand spuri-ous memories may develop. Applications of this model to storage and retrieval of naturally-arising generalized sequences in bioinformatics are presented. The model is shown to work well for detection of novel generalized sequences against a large database of stored sequences, and for removal of noisy black pixels in a probe image against a very large set of stored images.