2009 | OriginalPaper | Buchkapitel
A New Method of Morphological Associative Memories
verfasst von : Naiqin Feng, Xizheng Cao, Sujuan Li, Lianhui Ao, Shuangxi Wang
Erschienen in: Emerging Intelligent Computing Technology and Applications. With Aspects of Artificial Intelligence
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
The morphological associative memories (MAM) have many attractive advantages. However, they can not give a guarantee that morphological hetero-associative memories are perfect, even if input patterns are perfect. In addition, the problem with the associative memory matrixes
W
XY
and
M
XY
is that
W
XY
is incapable of handling dilative noise while
M
XY
is incapable of effectively handling erosive noise. In this paper, the new methods of MAM,
+
W
XY
and
+
M
XY
are proposed. The certain qualifications that make
+
W
XY
and
+
M
XY
be perfect memories are analyzed and proved. As far as the hetero-associative memories are concerned, although
+
W
XY
and
+
M
XY
are not perfect, they are complements to original
W
XY
and
M
XY
.
+
W
XY
is capable of handling dilative noise while
+
M
XY
is capable of effectively handling erosive noise. Therefore they can be put together with original
W
XY
and
M
XY
to learn from others’ strong points to offset ones’ own weakness and to make the effect of hetero-associative memories and pattern recognition better. The calculation results demonstrate that both
+
W
XY
and
+
M
XY
are effectual.