• 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

    Relative fisher information and natural gradient for learning large modular models

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    sun17b.pdf
    Size:
    1.304Mb
    Format:
    PDF
    Description:
    Published Version
    Download
    Type
    Conference Paper
    Authors
    Sun, Ke
    Nielsen, Frank
    KAUST Department
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    Date
    2017-01-01
    Permanent link to this record
    http://hdl.handle.net/10754/666740
    
    Metadata
    Show full item record
    Abstract
    Fisher information and natural gradient provided deep insights and powerful tools to artificial neural networks. However related analysis becomes more and more difficult as the learner's structure turns large and complex. This paper makes a preliminary step towards a new direction. We extract a local component from a large neural system, and define its relative Fisher information metric that describes accurately this small component, and is invariant to the other parts of the system. This concept is important because the geometry structure is much simplified and it can be easily applied to guide the learning of neural networks. We provide an analysis on a list of commonly used components, and demonstrate how to use this concept to further improve optimization.
    Sponsors
    The authors would like to thank the anonymous reviewers and Yann Ollivier for the helpful comments. This work was mainly conducted when the first author was a postdoctoral researcher at Ecole Polytechnique.
    Publisher
    MLResearchPress
    Conference/Event name
    34th International Conference on Machine Learning, ICML 2017
    ISBN
    9781510855144
    Additional Links
    http://proceedings.mlr.press/v70/sun17b.html
    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.