Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Predicting Deep Neural Network Generalization with Perturbation Response Curves
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-013-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-013-alpha.b-cdn.net
      • sl-yoda-v3-stream-013-beta.b-cdn.net
      • 1668715672.rsc.cdn77.org
      • 1420896597.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
            Predicting Deep Neural Network Generalization with Perturbation Response Curves
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Predicting Deep Neural Network Generalization with Perturbation Response Curves

            Dec 6, 2021

            Speakers

            YS

            Yair Schiff

            Speaker · 0 followers

            BQ

            Brian Quanz

            Speaker · 0 followers

            PD

            Payel Das

            Speaker · 0 followers

            About

            The field of Deep Learning is rich with empirical evidence of human-like performance on a variety of prediction tasks. However, despite these successes, the recent Predicting Generalization in Deep Learning (PGDL) NeurIPS 2020 competition suggests that there is a need for more robust and efficient measures of network generalization. In this work, we propose a new framework for evaluating the generalization capabilities of trained networks. We use perturbation response (PR) curves that capture th…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 128 followers

            About NeurIPS 2021

            Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.

            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

            SautiDB-Naija: A Nigerian L2 English Speech Corpus
            08:31

            SautiDB-Naija: A Nigerian L2 English Speech Corpus

            Tejumade Afonja, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis
            22:34

            Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis

            Yicheng Luo, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Automatic Symmetry Discovery with Lie Algebra Convolutional Network
            14:42

            Automatic Symmetry Discovery with Lie Algebra Convolutional Network

            Nima Dehmamy, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%

            Sculpting (human-like) AI systems by sculpting their (social) environments
            38:48

            Sculpting (human-like) AI systems by sculpting their (social) environments

            Pierre-Yves Oudeyer

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimation
            11:08

            Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimation

            Greg Lewis, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Automorphic Equivalence-aware Graph Neural Network
            12:48

            Automorphic Equivalence-aware Graph Neural Network

            Fengli Xu, …

            N2
            N2
            NeurIPS 2021 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 NeurIPS 2021