"RIV/60461373:22340/02:00007063" . . "Z(MSM 223400007)" . . . . "Proc. of 8th Int. Conference on Soft Computing MENDEL 2002" . "80-214-2135-5" . . "Brno" . . "Vysok\u00E9 u\u010Den\u00ED technick\u00E9 v Brn\u011B" . "self-organizing map (SOM); optimization; batch learning; metric space; graph; fuzzy"@en . . . . "S\u00FDkorov\u00E1, Kv\u011Bta" . . . . "Optimum SOM Distribution in Metric Spaces"@en . . "22340" . "Optimum SOM distribution is a combinatorial method of self-organization. The input patterns are supposed to be elements of metric space M with given distance measure. Let G be given undirected graph as a model of output metric space with node distance. The optimum SOM is a distribution of input patterns into graph nodes satisfying distance proportionality. There are various approaches to objective function design. The traditional penalty approach related to cluster analysis is compared with fuzzy logic function minimization. The discrete optimization task is solved as an NP-complete problem using combinatorial and stochastic global optimization techniques. Both traditional and fuzzy approaches are compared on illustrative example. The optimum SOM distribution is a general tool for the pattern categorization including patterns of observable states or outputs of technological process."@en . "Optimum SOM Distribution in Metric Spaces" . "RIV/60461373:22340/02:00007063!RIV/2004/MSM/223404/N" . "80-214-2135-5" . "9"^^ . . "3"^^ . "0"^^ . . . "0"^^ . "[0A0C0DE574CA]" . "657370" . "2002-06-05+02:00"^^ . "2"^^ . . . "Optimum SOM Distribution in Metric Spaces"@en . . "Kukal, Jarom\u00EDr" . . "Optimum SOM Distribution in Metric Spaces" . "287;291" . "Optimum SOM distribution is a combinatorial method of self-organization. The input patterns are supposed to be elements of metric space M with given distance measure. Let G be given undirected graph as a model of output metric space with node distance. The optimum SOM is a distribution of input patterns into graph nodes satisfying distance proportionality. There are various approaches to objective function design. The traditional penalty approach related to cluster analysis is compared with fuzzy logic function minimization. The discrete optimization task is solved as an NP-complete problem using combinatorial and stochastic global optimization techniques. Both traditional and fuzzy approaches are compared on illustrative example. The optimum SOM distribution is a general tool for the pattern categorization including patterns of observable states or outputs of technological process." . "Majerov\u00E1, Dana" .