Curtin University Homepage
  • Library
  • Help
    • Admin

    espace - Curtin’s institutional repository

    JavaScript is disabled for your browser. Some features of this site may not work without it.
    View Item 
    • espace Home
    • espace
    • Curtin Research Publications
    • View Item
    • espace Home
    • espace
    • Curtin Research Publications
    • View Item

    Learning parts-based representations with nonnegative restricted boltzmann machine

    Access Status
    Fulltext not available
    Authors
    Nguyeny, T.
    Tran, The Truyen
    Phungy, D.
    Venkateshy, S.
    Date
    2013
    Type
    Conference Paper
    
    Metadata
    Show full item record
    Citation
    Nguyeny, T. and Tran, T.T. and Phungy, D. and Venkateshy, S. 2013. Learning parts-based representations with nonnegative restricted boltzmann machine, pp. 133-148.
    Source Title
    Journal of Machine Learning Research
    ISSN
    1532-4435
    School
    Multi-Sensor Proc & Content Analysis Institute
    URI
    http://hdl.handle.net/20.500.11937/51761
    Collection
    • Curtin Research Publications
    Abstract

    © 2013 T.D. Nguyen, T. Tran, D. Phung & S. Venkatesh.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 nonlinear dimensionality 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.

    Related items

    Showing items related by title, author, creator and subject.

    • Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)
      Tran, The Truyen; Nguyen, T.; Phung, D.; Venkatesh, S. (2015)
      Electronic medical record (EMR) offers promises for novel analytics. However, manual feature engineering from EMR is labor intensive because EMR is complex – it contains temporal, mixed-type and multimodal data packed in ...
    • Relational evidence theory and spatial interpretation procedures.
      Pearce, Adrian (1996)
      Spatial interpretation involves the intelligent processing of images for learning, planning and visualisation. This involves building systems which learn to recognise patterns from the content of unconstrained data such ...
    • The Role of Teaching Models and Chemical Representations in Developing Students' Mental Models of Chemical Phenomena
      Chittleborough, Gail (2004)
      Chemical representations play a vital part in the teaching and learning of chemistry. The aim of this research was to investigate students’ understanding of chemical representations and to ascertain the influence of ...
    Advanced search

    Browse

    Communities & CollectionsIssue DateAuthorTitleSubjectDocument TypeThis CollectionIssue DateAuthorTitleSubjectDocument Type

    My Account

    Admin

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Follow Curtin

    • 
    • 
    • 
    • 
    • 

    CRICOS Provider Code: 00301JABN: 99 143 842 569TEQSA: PRV12158

    Copyright | Disclaimer | Privacy statement | Accessibility

    Curtin would like to pay respect to the Aboriginal and Torres Strait Islander members of our community by acknowledging the traditional owners of the land on which the Perth campus is located, the Whadjuk people of the Nyungar Nation; and on our Kalgoorlie campus, the Wongutha people of the North-Eastern Goldfields.