• Libraries
    • Log in to:
    View Item 
    •   MSpace Home
    • Faculty of Graduate Studies (Electronic Theses and Practica)
    • FGS - Electronic Theses and Practica
    • View Item
    •   MSpace Home
    • Faculty of Graduate Studies (Electronic Theses and Practica)
    • FGS - Electronic Theses and Practica
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Exploring redundancy in neural networks: pruning by genetic algorithm & filter energy

    Thumbnail
    View/Open
    janjic_sasa.pdf (1.944Mb)
    Date
    2018
    Author
    Janjic, Sasa
    Metadata
    Show full item record
    Abstract
    Much work has been done on making convolutional models larger and more robust, but recent works have shown there is significant redundancy, suggesting that they are vastly more complex than necessary. The goal of this thesis is to explore the degree to which the representational redundancy can be reduced. I contribute a weight pruning genetic algorithm, an energy-based filter pruning algorithm, and provide insights on model compression and structure. Evolved weight pruning of MNIST trained multilayer perceptrons and convolutional networks showed that in some cases 72.4% and 89.6% of layer parameters can be pruned without retraining, and yield improvements in test set accuracy. Energy-based filter pruning showed that ImageNet trained VGG and ResNet models also exhibit significant redundancy, with VGG layers incurring an average 3.2% loss in accuracy after 9.83% compression, and ResNet layers incurring an 3.30% loss after 87.94% compression for over one–third of the layers.
    URI
    http://hdl.handle.net/1993/33343
    Collections
    • FGS - Electronic Theses and Practica [25529]

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of MSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    Login

    Statistics

    View Usage Statistics

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV