Linear kernel combination using boosting

Alexis Lechervy (1) , Philippe-Henri Gosselin (2) , Frédéric Precioso (3)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
2 MIDI - Multimedia Indexation and Data Integration
3 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Equipe KEIA

In this paper, we propose a novel algorithm to design multi- class kernels based on an iterative combination of weak kernels in a schema inspired from the boosting framework. Our solution has a complexity lin- ear with the training set size. We evaluate our method for classification on a toy example by integrating our multi-class kernel into a kNN clas- sifier and comparing our results with a reference iterative kernel design method. We also evaluate our method for image categorization by con- sidering a classic image database and comparing our boosted linear kernel combination with the direct linear combination of all features in a linear SVM.

Domaines: Machine Learning [stat.ML]; Multimédia [cs.MM]

Alexis Lechervy, Philippe-Henri Gosselin, Frédéric Precioso. Linear kernel combination using boosting. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2012, Bruges, Belgium. pp.6. ⟨hal-00753155⟩