Title :

Bounds for Learning from Evolutionary-Related Data in the Realizable Case

Author(s) :

Kuželka, Ondřej [Auteur]
Cardiff University
Wang, Yuyi [Auteur]
Nanjing Institute of Geology and Palaeontology [NIGPAS-CAS]
Ramon, Jan [Auteur]
Machine Learning in Information Networks [MAGNET]

Conference title :

International Joint Conference on Artificial Intelligence (IJCAI)

City :

New York

Country :

Etats-Unis d'Amérique

Start date of the conference :

2016-07-09

Book title :

IJCAI 2016

Journal title :

Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) 2016

Publication date :

2016-07-11

English keyword(s) :

Machine learning
phylogenetics
Learning theory

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Bio-informatique [q-bio.QM]
Informatique [cs]/Théorie de l'information [cs.IT]
Statistiques [stat]/Machine Learning [stat.ML]

English abstract : [en]

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 re-alizable ...
Show more >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 re-alizable case, we prove PAC-type upper and lower bounds based on symmetries and matchings in such trees.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

European Project :

Mining Graphs and Networks: a Theory-based approach

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL