NAV Navbar
  • Research Papers
  • Research Papers

    Awesome - Most Cited Deep Learning Papers

    image

    SOURCE

    Awesome list criteria

    1. A list of top 100 deep learning papers published from 2012 to 2016 is suggested.
    2. If a paper is added to the list, another paper (usually from *More Papers from 2016" section) should be removed to keep top 100 papers. (Thus, removing papers is also important contributions as well as adding papers)
    3. Papers that are important, but failed to be included in the list, will be listed in More than Top 100 section.
    4. Please refer to New Papers and Old Papers sections for the papers published in recent 6 months or before 2012.

    Citation criteria

    < 6 months : New Papers (by discussion) - 2016 : +60 citations or "More Papers from 2016" - 2015 : +200 citations - 2014 : +400 citations - 2013 : +600 citations - 2012 : +800 citations - ~2012 : Old Papers (by discussion)


    Contents

    style

    More than Top 100


    Understanding / Generalization / Transfer

    convolution


    Optimization / Training Techniques

    training


    Unsupervised / Generative Models

    GAN


    Convolutional Neural Network Models

    convolution


    Image: Segmentation / Object Detection

    object detection


    Image / Video / Etc

    SR


    Natural Language Processing / RNNs

    RNN


    Speech / Other Domain

    wavenet


    Reinforcement Learning / Robotics

    RL


    More Papers from 2016

    gd


    New papers

    style_transfer

    Newly published papers (< 6 months) which are worth reading


    Old Papers

    dnn

    Classic papers published before 2012


    HW / SW / Dataset

    segmentation


    Book / Survey / Review

    book


    Video Lectures / Tutorials / Blogs

    Lectures

    image

    Tutorials

    Blogs


    Appendix: More than Top 100

    2016

    2015

    ~2014


    Acknowledgement

    MLBLR has taken this content from Terry T. Um's Github Page. We thank Terry T. Um for relesing this content with CC licence. We thank and appreciate his contributors as well!