Polynomial network classifier with discriminative feature extraction

Abstract : The polynomial neural network, or called polynomial network classifier (PNC), is a powerful nonlinear classifier that can separate classes of complicated distributions. A method that expands polynomial terms on principal subspace has yielded superior performance. In this paper, we aim to further improve the performance of the subspace-featurebased PNC. In the framework of discriminative feature extraction (DFE), we adjust the subspace parameters together with the network weights in supervised learning. Under the objective of minimum squared error, the parameters can be efficiently updated by stochastic gradient descent. In experiments on 13 datasets from the UCI Machine Learning Repository, we show that DFE can either improve the classification accuracy or reduce the network complexity. On seven datasets, the accuracy of PNC is competitive with support vector classifiers.
Type de document :
Communication dans un congrès
Joint IAPR International Workshops, SSPR 2006 and SPR 2006, Aug 2006, Hong-Kong / Chine, Springer, LNCS 4109/4109 (4109), pp.732-740, 2006, Lecture Notes in Computer Science. 〈10.1007/11815921_80〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00120417
Contributeur : Chine Publications Liama <>
Soumis le : mardi 19 décembre 2006 - 08:50:20
Dernière modification le : mardi 24 avril 2018 - 13:36:02
Document(s) archivé(s) le : jeudi 20 septembre 2012 - 16:06:47

Fichier

polymonial.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Cheng-Lin Liu. Polynomial network classifier with discriminative feature extraction. Joint IAPR International Workshops, SSPR 2006 and SPR 2006, Aug 2006, Hong-Kong / Chine, Springer, LNCS 4109/4109 (4109), pp.732-740, 2006, Lecture Notes in Computer Science. 〈10.1007/11815921_80〉. 〈inria-00120417〉

Partager

Métriques

Consultations de la notice

147

Téléchargements de fichiers

195