TY - GEN
T1 - On the issue of learning weights from observations for fuzzy signatures
AU - Mendis, B. Sumudu U.
AU - Gedeon, Tamás D.
AU - Kóczy, Lâszló T.
PY - 2006
Y1 - 2006
N2 - We investigate the issue of obtaining weights, which are associated with aggregation in fuzzy signatures, from real world data, Our approach will provide a way to extract the relevance of lower levels to the higher levels of the hierarchical fuzzy signature structure. We also handle the non-differentiability of max-min aggregation functions for gradient based learning. A mathematically proved method, which is found in the literature to approximate the derivatives of max-min functions, has been used. Copyright - World Automation Congress (WAC) 2006.
AB - We investigate the issue of obtaining weights, which are associated with aggregation in fuzzy signatures, from real world data, Our approach will provide a way to extract the relevance of lower levels to the higher levels of the hierarchical fuzzy signature structure. We also handle the non-differentiability of max-min aggregation functions for gradient based learning. A mathematically proved method, which is found in the literature to approximate the derivatives of max-min functions, has been used. Copyright - World Automation Congress (WAC) 2006.
KW - Fuzzy signatures
KW - Vector valued fuzzy sets
KW - Weighted aggregation
UR - http://www.scopus.com/inward/record.url?scp=36849073044&partnerID=8YFLogxK
U2 - 10.1109/WAC.2006.376058
DO - 10.1109/WAC.2006.376058
M3 - Conference contribution
SN - 1889335339
SN - 9781889335339
T3 - 2006 World Automation Congress, WAC'06
BT - 2006 World Automation Congress, WAC'06
PB - IEEE Computer Society
T2 - 2006 World Automation Congress, WAC'06
Y2 - 24 June 2006 through 26 June 2006
ER -