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

    Investigation of activation functions in deep belief network

    Access Status
    Fulltext not available
    Authors
    Lau, M.
    Lim, Hann
    Date
    2017
    Type
    Conference Paper
    
    Metadata
    Show full item record
    Citation
    Lau, M. and Lim, H. 2017. Investigation of activation functions in deep belief network, pp. 201-206.
    Source Title
    2017 2nd International Conference on Control and Robotics Engineering, ICCRE 2017
    DOI
    10.1109/ICCRE.2017.7935070
    ISBN
    9781509037735
    School
    Curtin Sarawak
    URI
    http://hdl.handle.net/20.500.11937/54534
    Collection
    • Curtin Research Publications
    Abstract

    © 2017 IEEE. Deep Belief Network (DBN) is made up of stacked Restricted Boltzmann Machine layers associated with global weight fine-tuning for pattern recognition. However, DBN suffers from vanishing gradient problem due to the saturation characteristic of activation function. Therefore, the selection of activation function in DBN is critical to reduce the network complexity and improve performance of pattern recognition. Unsaturated activation functions such as rectified linear unit and leaky rectified linear unit were recently proposed to avoid the effect of vanishing gradient for a deep learning neural network. In this paper, we investigated the network performance with both saturated and unsaturated activation functions. Besides that, the randomization of training samples would significantly improve the performance of DBN. The experimental results showed that hyperbolic tangent activation function achieved the lowest error rate which is 1.99% on MNIST handwritten digit dataset.

    Related items

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

    • Initiatives and partnerships in an Australian metropolitan obesity prevention system: a social network analysis
      Blackford, Krysten ; Leavy, Justine ; Vidler, Abbie-Clare; Chamberlain, D.; Pollard, Christina ; Riley, T.; Milligan, M.; Jancey, Jonine (2021)
      Background: Limited resources make prevention of complex population-level issues such as obesity increasingly challenging. Collaboration and partnerships between organisations operating in the same system can assist, ...
    • The human face of biobank networks for translational research
      Meir, K.; Gaffney, E.; Simeon-Dubach, D.; Ravid, R.; Watson, P.; Schacter, B.; Morente, M.; Bjugn, R.; Clark, B.; De Blasio, P.; Carpenter, J.; Deschenes, M.; Devereux, L.; Dhir, R.; Goebell, P.; Grizzle, W.; Hainaut, P.; Mes-Masson, A.; Miranda, L.; Parry-Jones, A.; Riegman, P.; Casali-Da-Rocha, J.; Soares, F.; Vaught, J.; Zeps, Nikolajs (2011)
      The biobanking literature frequently addresses donor and societal issues surrounding biobanking, but the biobanker's perspective is rarely highlighted. While not comprehensive, this article offers an overview of the human ...
    • CoNiFe-layered double hydroxide decorated Co-N-C network as a robust bi-functional oxygen electrocatalyst for zinc-air batteries
      Arafat, Yasir; Zhong, Yijun; Azhar, M.R.; Asif, M.; Tadé, Moses O.; Shao, Zongping (2023)
      Rechargeable zinc-air batteries (ZABs) are cost-effective energy storage devices and display high-energy density. To realize high round-trip energy efficiency, it is critical to develop durable bi-functional air electrodes, ...
    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.