We describe a set of associative memories useful to recall real-valued patterns in the presence of mixed noise. Numerical and real examples are provided to show the efficiency of the proposal. Conditions under which the proposed memories are able to recall patterns either from the fundamental set of patterns and from distorted versions of them are also given.
Citation:
Humberto Sossa, Ricardo Barr?, Jos? L. Oropeza, H?ctor Cort?, "Associative Memory Based Real-Valued Pattern Recall," enc, pp.206-212, Fifth Mexican International Conference in Computer Science (ENC'04), 2004