Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Group Equivariant Subsampling
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-016-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-016-alpha.b-cdn.net
      • sl-yoda-v3-stream-016-beta.b-cdn.net
      • 1504562137.rsc.cdn77.org
      • 1896834465.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
            Group Equivariant Subsampling
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Group Equivariant Subsampling

            Dec 6, 2021

            Speakers

            JX

            Jin Xu

            Speaker · 0 followers

            HK

            Hyunjik Kim

            Speaker · 0 followers

            TR

            Tom Rainforth

            Speaker · 0 followers

            About

            Subsampling is used in convolutional neural networks (CNNs) in the form of pooling or strided convolutions, to reduce the spatial dimensions of feature maps and to allow the receptive fields to grow exponentially with depth. However, it is known that such subsampling operations are not translation equivariant, unlike convolutions that are translation equivariant. Here, we first introduce translation equivariant subsampling/upsampling layers that can be used to construct exact translation equivar…

            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

            Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
            13:51

            Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

            Liming Jiang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            A Brief Summary on Covid-19 Pandemic & Machine Learning Approaches
            02:43

            A Brief Summary on Covid-19 Pandemic & Machine Learning Approaches

            Ezgi Korkmaz

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Defending the undefendable... Why I support peer reviewing
            31:10

            Defending the undefendable... Why I support peer reviewing

            Dima Damen

            N2
            N2
            NeurIPS 2021 3 years ago

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

            LatinX in AI (LXAI) Research @ NeurIPS 2021
            5:14:06

            LatinX in AI (LXAI) Research @ NeurIPS 2021

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL
            14:03

            Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

            Charles Packer, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            An analysis of Ermakov-Zolotukhin quadrature using kernels
            15:09

            An analysis of Ermakov-Zolotukhin quadrature using kernels

            Ayoub Belhadji

            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