Reference : Towards sub-quadratic learning of probability density models in the form of mixtures ...
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/24937
Towards sub-quadratic learning of probability density models in the form of mixtures of trees
English
Schnitzler, François mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Leray, Philippe mailto [Ecole Polytechnique de l’Université de Nantes > Laboratoire d’Informatique de Nantes Atlantique > Knowledge and Decision Team > >]
Wehenkel, Louis mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Apr-2010
219-224
Yes
No
International
18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
28 - 30 April 2010
Michel Verleysen
Bruges
Belgium
[en] bayesian networks ; mixture of trees ; perturb and combine ; Chow-Liu ; unsupervised learning
[en] We consider randomization schemes of the Chow-Liu algorithm from weak (bagging, of quadratic complexity) to strong ones (full random sampling, of linear complexity), for learning probability density models in the form of mixtures of Markov trees. Our empirical study on high-dimensional synthetic problems shows that, while bagging is the most accurate scheme on average, some of the stronger randomizations remain very competitive in terms of accuracy, specially for small sample sizes.
Systèmes et modélisation
Fonds pour la formation à la Recherche dans l'Industrie et dans l'Agriculture (Communauté française de Belgique) - FRIA ; Wallonie-Bruxelles International, FNRS, Ministère Français des Affaires étrangères et Européennes, Ministère français de l'Enseignement supérieur et de la Recherche dans le cadre des partenariats Hubert Curien ; Biomagnet IUAP network of the Belgian Science Policy Office ; Pascal2 network of excellence of the EC
Researchers
http://hdl.handle.net/2268/24937
http://www.montefiore.ulg.ac.be/~schnitzl/Publications_files/ESANN_2010_schnitzler_leray_wehenkel_final.pdf

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
es2010-104.pdfNo commentaryPublisher postprint713.42 kBView/Open

Additional material(s):

File Commentary Size Access
Open access
presentation_ESANN.pdfnull1.8 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.