Structured representation learning from complex data Nguygen, Tu Dinh 2015, Structured representation learning from complex data, Ph.D. thesis, School of Information Technology, Deakin University. Attached Files Name Description MIMEType Size Downloads nguyen-structuredrepresentation-2015A.pdf Connect to thesis application/pdf 10.12MB 405 Title Structured representation learning from complex data Author Nguygen, Tu Dinh Institution Deakin University School School of Information Technology Faculty Faculty of Science Engineering and Built Environment Degree type Research doctorate Degree name Ph.D. Thesis advisor Phung, Dinh orcid.org/0000-0002-9977-8247 Venkatesh, Svetha orcid.org/0000-0001-8675-6631 Tran, Truyen orcid.org/0000-0001-6531-8907 Date submitted 2015-04 Keyword(s) statistical machine learning annotated labels restricted Boltzmann machine structured representations Summary This thesis advances several theoretical and practical aspects of the recently introduced restricted Boltzmann machine - a powerful probabilistic and generative framework for modelling data and learning representations. The contributions of this study represent a systematic and common theme in learning structured representations from complex data. Language eng Field of Research 080109 Pattern Recognition and Data Mining Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences Description of original xx, 198, [4] pages : illustrations, tables, graphs Copyright notice ©The Author. All Rights Reserved Free to Read? Yes Persistent URL http://hdl.handle.net/10536/DRO/DU:30079713 Document type: Thesis Collections: Higher degree theses (Open Access) Open Access Collection   Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. 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. Versions Version Filter Type Fri, 20 Nov 2015, 14:33:31 EST Mon, 23 Nov 2015, 08:13:57 EST Wed, 02 Dec 2015, 10:41:02 EST Wed, 02 Dec 2015, 10:46:02 EST Thu, 09 Mar 2017, 07:18:10 EST Thu, 09 Mar 2017, 09:10:37 EST Tue, 07 Aug 2018, 11:07:00 EST Fri, 07 Sep 2018, 19:02:44 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 0 times in Scopus Search Google Scholar Access Statistics: 421 Abstract Views, 410 File Downloads  -  Detailed Statistics Created: Fri, 20 Nov 2015, 14:33:21 EST by Prue Plummer