Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Robust Models Are More Interpretable Because Attributions Look Normal
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-004-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-004-alpha.b-cdn.net
      • sl-yoda-v2-stream-004-beta.b-cdn.net
      • 1685195716.rsc.cdn77.org
      • 1239898752.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
            Robust Models Are More Interpretable Because Attributions Look Normal
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Robust Models Are More Interpretable Because Attributions Look Normal

            Jul 19, 2022

            Speakers

            ZW

            Zifan Wang

            Speaker · 0 followers

            MF

            Matt Fredrikson

            Speaker · 0 followers

            AD

            Anupam Datta

            Speaker · 0 followers

            Organizer

            I2
            I2

            ICML 2022

            Account · 493 followers

            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

            Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees
            04:42

            Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees

            Verónica Álvarez, …

            I2
            I2
            ICML 2022 3 years ago

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

            Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learned
            03:43

            Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learned

            Sören Mindermann, …

            I2
            I2
            ICML 2022 3 years ago

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

            Training Your Sparse Neural Network Better with Any Mask
            05:22

            Training Your Sparse Neural Network Better with Any Mask

            Ajay Jaiswal, …

            I2
            I2
            ICML 2022 3 years ago

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

            Generating Distributional Adversarial Examples to Evade Statistical Detectors
            05:30

            Generating Distributional Adversarial Examples to Evade Statistical Detectors

            Yigitcan Kaya, …

            I2
            I2
            ICML 2022 3 years ago

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

            Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
            04:00

            Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics

            Shoaib Ahmed Siddiqui, …

            I2
            I2
            ICML 2022 3 years ago

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

            In defense of dual-encoders for neural ranking
            05:18

            In defense of dual-encoders for neural ranking

            Aditya Krishna Menon, …

            I2
            I2
            ICML 2022 3 years ago

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

            Interested in talks like this? Follow ICML 2022