Avancerad sökning

Hittade 1 avhandling som matchar ovanstående sökkriterier.

1. 1. Approximations of Bayes Classifiers for Statistical Learning of Clusters

   Författare :Magnus Ekdahl; Timo Koski; Jukka Corander; Linköpings universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Pattern Recognition; Stochastic Complexity; Naïve Bayes; Bayesian Network; Classification; Clustering; Chow-Liu trees; Mathematical statistics; Matematisk statistik;

   Sammanfattning : It is rarely possible to use an optimal classifier. Often the classifier used for a specific problem is an approximation of the optimal classifier. Methods are presented for evaluating the performance of an approximation in the model class of Bayesian Networks. LÄS MER