• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage StatisticsView Google Analytics Statistics

    Lottery ticket hypothesis : using deeper conv nets and on Atari games

    Thumbnail
    View/Open
    201811062.pdf (596.8Kb)
    Date
    2020
    Author
    Suresh, Shweta
    Metadata
    Show full item record
    Abstract
    The lottery ticket hypothesis proposes that the over-parameterization of deep neural networks helps training by increasing the probability of a lucky subnetwork initialization being present rather than by helping the optimization process. This phenomenon suggests that initialization strategies for DNNs can be improved substantially, but the lottery ticket hypothesis has only been previously tested on MNIST and CIFAR-10 datasets with architectures- VGG19 and Resnet18. Here we evaluate whether winning ticket initializations exist in deeper convolutional neural network architectures and fully connected networks and also on reinforcement learning domain on atari games.
    URI
    http://drsr.daiict.ac.in//handle/123456789/969
    Collections
    • M Tech Dissertations [923]

    Resource Centre copyright © 2006-2017 
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     


    Resource Centre copyright © 2006-2017 
    Contact Us | Send Feedback
    Theme by 
    Atmire NV