Abstract : Latent topic models have proven to be an efficient tool for modeling multitopic count data. One of the most well-known models is the latent Dirichlet allocation (LDA). In this paper we propose two improvements for LDA using generalized Dirichlet and Beta-Liouville prior assumptions. Moreover, we apply an online learning approach for both introduced approaches. We choose a challenging application namely natural scene classification for comparison and evaluation purposes.
David Hutchison; Takeo Kanade; Bernhard Steffen; Demetri Terzopoulos; Doug Tygar; Gerhard Weikum; Linawati; Made Sudiana Mahendra; Erich J. Neuhold; A Min Tjoa; Ilsun You; Josef Kittler; Jon M. Kleinberg; Alfred Kobsa; Friedemann Mattern; John C. Mitchell; Moni Naor; Oscar Nierstrasz; C. Pandu Rangan. 2nd Information and Communication Technology - EurAsia Conference (ICT-EurAsia), Apr 2014, Bali, Indonesia. Springer, Lecture Notes in Computer Science, LNCS-8407, pp.286-295, 2014, Information and Communication Technology. 〈10.1007/978-3-642-55032-4_28〉
https://hal.inria.fr/hal-01397223
Contributeur : Hal Ifip
<>
Soumis le : mardi 15 novembre 2016 - 15:47:28
Dernière modification le : jeudi 26 juillet 2018 - 14:08:02
Document(s) archivé(s) le : jeudi 16 mars 2017 - 13:22:07
Ali Bakhtiari, Nizar Bouguila. Online Learning for Two Novel Latent Topic Models. David Hutchison; Takeo Kanade; Bernhard Steffen; Demetri Terzopoulos; Doug Tygar; Gerhard Weikum; Linawati; Made Sudiana Mahendra; Erich J. Neuhold; A Min Tjoa; Ilsun You; Josef Kittler; Jon M. Kleinberg; Alfred Kobsa; Friedemann Mattern; John C. Mitchell; Moni Naor; Oscar Nierstrasz; C. Pandu Rangan. 2nd Information and Communication Technology - EurAsia Conference (ICT-EurAsia), Apr 2014, Bali, Indonesia. Springer, Lecture Notes in Computer Science, LNCS-8407, pp.286-295, 2014, Information and Communication Technology. 〈10.1007/978-3-642-55032-4_28〉. 〈hal-01397223〉
