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

            VAEs meet Diffusion Models: Efficient and High-Fidelity Generation
            12:34

            VAEs meet Diffusion Models: Efficient and High-Fidelity Generation

            Kushagra Pandey, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Probabilistic Tensor Decomposition of Neural Population Spiking Activity
            13:50

            Probabilistic Tensor Decomposition of Neural Population Spiking Activity

            Hugo Soulat, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            DeepRNG: Towards Deep RL-Assisted Generative Testing of Software
            07:25

            DeepRNG: Towards Deep RL-Assisted Generative Testing of Software

            Kenyon Tsai, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Frank Wolfe in Probability Space
            14:53

            Frank Wolfe in Probability Space

            Carson Kent, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            A Modern Self-Referential Weight Matrix That Learns to Modify Itself
            04:16

            A Modern Self-Referential Weight Matrix That Learns to Modify Itself

            Kazuki Irie, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Billion-Scale Approximate Nearest Neighbor Search Challenge
            21:04

            Billion-Scale Approximate Nearest Neighbor Search Challenge

            Harsha Simhadri, …

            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