< Terug naar vorige pagina


Bounds for learning from evolutionary-related data in the realizable case

Tijdschriftbijdrage - Boekhoofdstuk Conferentiebijdrage

This paper deals with the generalization ability of classifiers trained from non-iid evolutionary-related data in which all training and testing examples correspond to leaves of a phylogenetic tree. For the realizable case, we prove PAC-type upper and lower bounds based on symmetries and matchings in such trees.
Tijdschrift: IJCAI International Joint Conference on Artificial Intelligence
ISSN: 1045-0823
Volume: 2016-Janua
Pagina's: 1655
Jaar van publicatie:2016