Boltzmann Machine and its Applications in Image Recognition

Abstract : The overfitting problems commonly exist in neural networks and RBM models. In order to alleviate the overfitting problem, lots of research has been done. This paper built Weight uncertainty RBM model based on maximum likelihood estimation. And in the experimental section, this paper verified the effectiveness of the Weight uncertainty Deep Belief Network and the Weight uncertainty Deep Boltzmann Machine. In order to improve the images recognition ability, we introduce the spike-and-slab RBM (ssRBM) to our Weight uncertainty RBM and then build the Weight uncertainty spike-and-slab Deep Boltzmann Machine (wssDBM). The experiments showed that, the Weight uncertainty RBM, Weight uncertainty DBN and Weight uncertainty DBM were effective compared with the dropout method. At last, we validate the effectiveness of wssDBM in experimental section.
Type de document :
Communication dans un congrès
9th International Conference on Intelligent Information Processing (IIP), Nov 2016, Melbourne, VIC, Australia. IFIP Advances in Information and Communication Technology, AICT-486, pp.108-118, 2016, Intelligent Information Processing VIII. 〈10.1007/978-3-319-48390-0_12〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01614991
Contributeur : Hal Ifip <>
Soumis le : mercredi 11 octobre 2017 - 16:57:51
Dernière modification le : vendredi 3 novembre 2017 - 22:24:06
Document(s) archivé(s) le : vendredi 12 janvier 2018 - 15:38:50

Fichier

 Accès restreint
Fichier visible le : 2019-01-01

Connectez-vous pour demander l'accès au fichier

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Shifei Ding, Jian Zhang, Nan Zhang, Yanlu Hou. Boltzmann Machine and its Applications in Image Recognition. 9th International Conference on Intelligent Information Processing (IIP), Nov 2016, Melbourne, VIC, Australia. IFIP Advances in Information and Communication Technology, AICT-486, pp.108-118, 2016, Intelligent Information Processing VIII. 〈10.1007/978-3-319-48390-0_12〉. 〈hal-01614991〉

Partager

Métriques

Consultations de la notice

33