Distance Metric Learning-Based Conformal Predictor - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Distance Metric Learning-Based Conformal Predictor

Résumé

In order to improve the computational efficiency of conformal predictor, distance metric learning methods were used in the algorithm. The process of learning was divided into two stages: offline learning and online learning. Firstly, part of the training data was used in distance metric learning to get a space transformation matrix in the offline learning stage; Secondly, standard CP-KNN was conducted on the remaining training data with a nonconformity measure function defined by K nearest neighbors classifier in the transformed space. Experimental results on three UCI datasets demonstrate the efficiency of the new algorithm.
Fichier principal
Vignette du fichier
978-3-642-33412-2_26_Chapter.pdf (449.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01523097 , version 1 (16-05-2017)

Licence

Paternité

Identifiants

Citer

Fan Yang, Zhigang Chen, Guifang Shao, Huazhen Wang. Distance Metric Learning-Based Conformal Predictor. 8th International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2012, Halkidiki, Greece. pp.254-259, ⟨10.1007/978-3-642-33412-2_26⟩. ⟨hal-01523097⟩
63 Consultations
59 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More