Mendis, B SumuduGedeon, Tamas (Tom)Koczy, Lazlo2015-12-08July 24-26http://hdl.handle.net/1885/36828We 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.Keywords: Hierarchical fuzzy signature; Vector valued fuzzy sets; Weighted aggregation; Approximation theory; Functions; Hierarchical systems; Learning systems; Mathematical morphology; Optimization; Fuzzy sets Fuzzy signatures; Vector valued fuzzy sets; Weighted aggregation200610.1109/WAC.2006.3760582015-12-08