Learning parts-based representations with nonnegative restricted boltzmann machine Nguyen, Tu Dinh, Tran, Truyen, Phung, Dinh and Venkatesh, Svetha 2013, Learning parts-based representations with nonnegative restricted boltzmann machine, in ACML 2013 : Proceedings of the 5th Asian Conference on Machine Learning, [The Conference], [Canberra, A.C.T.], pp. 133-148. Attached Files Name Description MIMEType Size Downloads Title Learning parts-based representations with nonnegative restricted boltzmann machine Author(s) Nguyen, Tu Dinh Tran, Truyen orcid.org/0000-0001-6531-8907 Phung, Dinh orcid.org/0000-0002-9977-8247 Venkatesh, Svetha orcid.org/0000-0001-8675-6631 Conference name Asian Conference on Machine Learning (5th : 2013 : Canberra, Australian Capital Territory)) Conference location Canberra, Australian Capital Territory Conference dates 2013/11/13 - 2013/11/15 Title of proceedings ACML 2013 : Proceedings of the 5th Asian Conference on Machine Learning Publication date 2013 Start page 133 End page 148 Total pages 16 Publisher [The Conference] Place of publication [Canberra, A.C.T.] Keyword(s) parts-based representation nonnegative restricted Boltzmann machines learning representation semantic features Summary The success of any machine learning system depends critically on effective representations of data. In many cases, especially those in vision, it is desirable that a representation scheme uncovers the parts-based, additive nature of the data. Of current representation learning schemes, restricted Boltzmann machines (RBMs) have proved to be highly effective in unsupervised settings. However, when it comes to parts-based discovery, RBMs do not usually produce satisfactory results. We enhance such capacity of RBMs by introducing nonnegativity into the model weights, resulting in a variant called nonnegative restricted Boltzmann machine (NRBM). The NRBM produces not only controllable decomposition of data into interpretable parts but also offers a way to estimate the intrinsic nonlineardimensionality of data. We demonstrate the capacity of our model on well-known datasets of handwritten digits, faces and documents. The decomposition quality on images is comparable with or better than what produced by the nonnegative matrix factorisation (NMF), and the thematic features uncovered from text are qualitatively interpretable in a similar manner to that of the latent Dirichlet allocation (LDA). However, the learnt features, when used for classification, are more discriminative than those discovered by both NMF and LDA and comparable with those by RBM. Language eng Field of Research 080109 Pattern Recognition and Data Mining 080702 Health Informatics Socio Economic Objective 0 Not Applicable HERDC Research category E1.1 Full written paper - refereed Copyright notice ©2013, The Authors Persistent URL http://hdl.handle.net/10536/DRO/DU:30081487 Document type: Conference Paper Collection: School of Information Technology Related Links Link Description Connect to Elements publication management system Go to link with your DU access privileges   Connect to published version Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Fri, 19 Feb 2016, 11:56:59 EST Sat, 20 Feb 2016, 04:02:00 EST Thu, 08 Jun 2017, 10:50:59 EST Thu, 08 Jun 2017, 10:53:38 EST Thu, 08 Jun 2017, 10:55:17 EST Wed, 14 Jun 2017, 06:05:31 EST Wed, 14 Jun 2017, 15:17:56 EST Sat, 17 Jun 2017, 02:40:33 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 5 times in Scopus Search Google Scholar Access Statistics: 36 Abstract Views, 2 File Downloads  -  Detailed Statistics Created: Fri, 19 Feb 2016, 11:56:59 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.