Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Knowledge distillation via softmax regression representation learning
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-003-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-003-alpha.b-cdn.net
      • sl-yoda-v2-stream-003-beta.b-cdn.net
      • 1544410162.rsc.cdn77.org
      • 1005514182.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Knowledge distillation via softmax regression representation learning
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Knowledge distillation via softmax regression representation learning

            May 3, 2021

            Speakers

            JY

            Jing Yang

            Speaker · 0 followers

            BM

            Brais Martinez

            Speaker · 0 followers

            AB

            Adrian Bulat

            Speaker · 0 followers

            About

            This paper addresses the problem of model compression via knowledge distillation. We advocate for a method that optimizes the output feature of the penultimate layer of the student network and hence is directly related to representation learning. Previous distillation methods which typically impose direct feature matching between the student and the teacher do not take into account the classification problem at hand. On the contrary, our distillation method decouples representation learning and…

            Organizer

            I2
            I2

            ICLR 2021

            Account · 899 followers

            Categories

            AI & Data Science

            Category · 10.8k presentations

            About ICLR 2021

            The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Moral Scenarios for Reinforcement Learning Agents
            03:22

            Moral Scenarios for Reinforcement Learning Agents

            Dan Hendrycks, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Randomized Automatic Differentiation
            12:09

            Randomized Automatic Differentiation

            Deniz Oktay, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Lossy Image Compression with Normalizing Flows
            05:10

            Lossy Image Compression with Normalizing Flows

            L. Helminger, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Improved Estimation of Concentration Under lp-Norm Distance Metrics Using Half Spaces
            06:46

            Improved Estimation of Concentration Under lp-Norm Distance Metrics Using Half Spaces

            Jack Prescott, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Improved Contrastive Divergence Training of Energy Based Models
            26:30

            Improved Contrastive Divergence Training of Energy Based Models

            Yilun Du, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Language-Agnostic Representation Learning of Source Code from Structure and Context
            04:34

            Language-Agnostic Representation Learning of Source Code from Structure and Context

            Daniel Zügner, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow ICLR 2021