• Login
    View Item 
    •   Home
    • Research
    • Conference Papers
    • View Item
    •   Home
    • Research
    • Conference Papers
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguideTheses and Dissertations LibguideSubmit an Item

    Statistics

    Display statistics

    Uncertainty-guided Continual Learning with Bayesian Neural Networks

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Conference Paperfile1.pdf
    Size:
    392.5Kb
    Format:
    PDF
    Description:
    Post-print
    Download
    Type
    Conference Paper
    Authors
    Ebrahimi, Sayna
    Elhoseiny, Mohamed cc
    Darrell, Trevor
    Rohrbach, Marcus
    KAUST Department
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    Date
    2020-03-11
    Preprint Posting Date
    2019-06-06
    Submitted Date
    2019-09-25
    Permanent link to this record
    http://hdl.handle.net/10754/662644
    
    Metadata
    Show full item record
    Abstract
    Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation and extra computation to measure the parameters' $\textit{importance}$. In contrast, we propose Uncertainty-guided Continual Bayesian Neural Networks (UCB), where the learning rate adapts according to the uncertainty defined in the probability distribution of the weights in networks. Uncertainty is a natural way to identify $\textit{what to remember}$ and $\textit{what to change}$ as we continually learn, and thus mitigate catastrophic forgetting. We also show a variant of our model, which uses uncertainty for weight pruning and retains task performance after pruning by saving binary masks per tasks. We evaluate our UCB approach extensively on diverse object classification datasets with short and long sequences of tasks and report superior or on-par performance compared to existing approaches. Additionally, we show that our model does not necessarily need task information at test time, i.e. it does not presume knowledge of which task a sample belongs to.
    Sponsors
    Work done while at Facebook AI Research.
    Publisher
    ICLR
    Conference/Event name
    International Conference on Learning Representations (ICLR) 2020
    arXiv
    1906.02425
    Additional Links
    https://arxiv.org/pdf/1906.02425
    https://openreview.net/forum?id=HklUCCVKDB
    Relations
    Is Supplemented By:
    • [Software]
      Title: SaynaEbrahimi/UCB: Original PyTorch implementation of Uncertainty-guided Continual Learning with Bayesian Neural Networks, ICLR 2020. Publication Date: 2019-02-04. github: SaynaEbrahimi/UCB Handle: 10754/667505
    Collections
    Conference Papers; Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2023  DuraSpace
    Quick Guide | Contact Us | KAUST University Library
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.