Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-011-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-011-alpha.b-cdn.net
      • sl-yoda-v3-stream-011-beta.b-cdn.net
      • 1150868944.rsc.cdn77.org
      • 1511650057.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
            Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Neural Ensemble Search for Uncertainty Estimation and Dataset Shift

            Dec 6, 2021

            Speakers

            SZ

            Sheheryar Zaidi

            Speaker · 0 followers

            AZ

            Arber Zela

            Speaker · 0 followers

            TE

            Thomas Elsken

            Speaker · 0 followers

            About

            Ensembles of neural networks achieve superior performance compared to stand-alone networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. Deep ensembles, a state-of-the-art method for uncertainty estimation, only ensemble random initializations of a fixed architecture. Instead, we propose two methods for automatically constructing ensembles with varying architectures, which implicitly trade-off individual architectures' strengths against the ensemble's diversity a…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 1.9k 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

            Self-Instantiated Recurrent Units with Dynamic Soft Recursion
            09:53

            Self-Instantiated Recurrent Units with Dynamic Soft Recursion

            Aston Zhang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management
            07:56

            Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management

            Cécile Logé, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Creating a Coefficient of Change in the Builtenvironment After a Natural Disaster
            05:34

            Creating a Coefficient of Change in the Builtenvironment After a Natural Disaster

            Karla Saldana Ochoa

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates
            05:07

            Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates

            Litian Liang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Data Agnostic Image Annotation
            01:54

            Data Agnostic Image Annotation

            Abbaas Alif Mohamed Nishar, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Lesan - Machine Translation for Low Resource Languages
            11:23

            Lesan - Machine Translation for Low Resource Languages

            Asmelash Teka Hadgu, …

            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