In A fast learning algorithm for deep belief nets, the authors use the term "undirected associative memory". I am not sure what they are referring to, and unfortunately Google searches for this term all seem to refer back to this paper. This leads me to believe the authors are unique in using this terminology and it is probably synonymous with some more commonly used term. Perhaps in 2006 scholars knew what it was, but I can't be sure.
Is it just a Hopfield Network?