TY - JOUR
T1 - Sparsely connected hopfield networks for the recognition of correlated pattern sets
AU - Stiefvater, Thomas
AU - Müller, Klaus Robert
AU - Janssen, Herbert
N1 - Funding Information:
K-RM gratefully acknowledges partial financial support by LandesgraduiertenFordemg Baden-Wiirttemberg and A Glenz. This work is part of the PhD thesis of K-RM done at the Department of Logics, University of Karlsruhe. HJ is partiauy supported by the German Federal Department of Research and Technology (BMFT) under Grant No ITR8800K4. It is a pleasure to thank H Homer and R KUhn for valuable discussions.
PY - 1993
Y1 - 1993
N2 - A sparsely connected Hopfield network for the recognition of natural, highly correlated video images is proposed. A general design mechanism for the construction of a local neighbourhood structure using a statistical analysis of an arbitrary given pattern set is suggested. The duality between learning and dilution is employed and different learning and dilution schemes are discussed. The practical use and the efficiency of the model are shown in simulations of a large network (N=12288). The authors use a set of natural patterns with high inter pattern correlations and a high site correlation within each pattern, in which the correlations are given and not constructed by special rules as for highly correlated random pattern sets. The results obtained are analysed for different coding types of the binary pattern set.
AB - A sparsely connected Hopfield network for the recognition of natural, highly correlated video images is proposed. A general design mechanism for the construction of a local neighbourhood structure using a statistical analysis of an arbitrary given pattern set is suggested. The duality between learning and dilution is employed and different learning and dilution schemes are discussed. The practical use and the efficiency of the model are shown in simulations of a large network (N=12288). The authors use a set of natural patterns with high inter pattern correlations and a high site correlation within each pattern, in which the correlations are given and not constructed by special rules as for highly correlated random pattern sets. The results obtained are analysed for different coding types of the binary pattern set.
UR - http://www.scopus.com/inward/record.url?scp=36149035298&partnerID=8YFLogxK
U2 - 10.1088/0954-898X_4_3_005
DO - 10.1088/0954-898X_4_3_005
M3 - Article
AN - SCOPUS:36149035298
SN - 0954-898X
VL - 4
SP - 313
EP - 336
JO - Network: Computation in Neural Systems
JF - Network: Computation in Neural Systems
IS - 3
ER -