Rice Univesrity Logo
    • FAQ
    • Deposit your work
    • Login
    View Item 
    •   Rice Scholarship Home
    • Faculty & Staff Research
    • Faculty Publications
    • View Item
    •   Rice Scholarship Home
    • Faculty & Staff Research
    • Faculty Publications
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    A Probabilistic Framework for Deep Learning

    Thumbnail
    Name:
    ToDL-NIPS2016.pdf
    Size:
    2.854Mb
    Format:
    PDF
    View/Open
    Author
    Patel, Ankit B.; Nguyen, Tan; Baraniuk, Richard G.
    Date
    2016
    Abstract
    We develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables. We demonstrate that max-sum inference in the DRMM yields an algorithm that exactly reproduces the operations in deep convolutional neural networks (DCNs), providing a first principles derivation. Our framework provides new insights into the successes and shortcomings of DCNs as well as a principled route to their improvement. DRMM training via the Expectation-Maximization (EM) algorithm is a powerful alternative to DCN back-propagation, and initial training results are promising. Classification based on the DRMM and other variants outperforms DCNs in supervised digit classification, training 2-3x faster while achieving similar accuracy. Moreover, the DRMM is applicable to semi-supervised and unsupervised learning tasks, achieving results that are state-of-the-art in several categories on the MNIST benchmark and comparable to state of the art on the CIFAR10 benchmark.
    Description
    NEWS COVERAGE: A news release based on this journal publication is available online: http://news.rice.edu/2016/12/16/rice-baylor-team-sets-new-mark-for-deep-learning/
    Citation
    Patel, Ankit B., Nguyen, Tan and Baraniuk, Richard G.. "A Probabilistic Framework for Deep Learning." Advances in Neural Information Processing Systems 29, (2016) Neural Information Processing Systems Foundation, Inc.: https://hdl.handle.net/1911/93745.
    Type
    Journal article
    Publisher
    Neural Information Processing Systems Foundation, Inc.
    Citable link to this page
    https://hdl.handle.net/1911/93745
    Link to related resources
    http://papers.nips.cc/paper/6231-a-probabilistic-framework-for-deep-learning
    Metadata
    Show full item record
    Collections
    • ECE Publications [1443]
    • Faculty Publications [4988]

    Home | FAQ | Contact Us | Privacy Notice | Accessibility Statement
    Managed by the Digital Scholarship Services at Fondren Library, Rice University
    Physical Address: 6100 Main Street, Houston, Texas 77005
    Mailing Address: MS-44, P.O.BOX 1892, Houston, Texas 77251-1892
    Site Map

     

    Searching scope

    Browse

    Entire ArchiveCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsTypeThis CollectionBy Issue DateAuthorsTitlesSubjectsType

    My Account

    Login

    Statistics

    View Usage Statistics

    Home | FAQ | Contact Us | Privacy Notice | Accessibility Statement
    Managed by the Digital Scholarship Services at Fondren Library, Rice University
    Physical Address: 6100 Main Street, Houston, Texas 77005
    Mailing Address: MS-44, P.O.BOX 1892, Houston, Texas 77251-1892
    Site Map