We present a new associative memory model that stores arbitrary bipolar pat
terns without the problems we can find in other models like BAM or LAM. Aft
er identifying those problems we show the new memory topology and we explai
n its learning and recall stages. Mathematical demonstrations are provided
to prove that the new memory model guarantees the perfect retrieval of ever
y stored pattern and also to prove that whatever the input of the memory is
, it operates as a nearest neighbor classifier. (C) 2000 John Wiley & Sons,
Inc.