Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Residual Pathway Priors for Soft Equivariance Constraints
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-001-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-001-alpha.b-cdn.net
      • sl-yoda-v2-stream-001-beta.b-cdn.net
      • 1824830694.rsc.cdn77.org
      • 1979322955.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
            Residual Pathway Priors for Soft Equivariance Constraints
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Residual Pathway Priors for Soft Equivariance Constraints

            Dec 6, 2021

            Speakers

            MF

            Marc Finzi

            Speaker · 1 follower

            GB

            Greg Benton

            Speaker · 0 followers

            AGW

            Andrew Gordon Wilson

            Speaker · 0 followers

            About

            Models such as convolutional neural networks restrict the hypothesis space to a set of functions satisfying equivariance constraints, and improve generalization in problems by capturing relevant symmetries. However, symmetries are often only partially respected, preventing models with restriction biases from fitting the data. We introduce Residual Pathway Priors (RPPs) as a method for converting hard architectural constraints into soft priors, guiding models towards structured solutions while re…

            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

            PCA Retargeting: Encoding Linear Shape Models as Convolutional Mesh Autoencoders
            19:50

            PCA Retargeting: Encoding Linear Shape Models as Convolutional Mesh Autoencoders

            Eimear O'Sullivan

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Environment Generation for Zero-Shot Compositional Reinforcement Learning
            08:40

            Environment Generation for Zero-Shot Compositional Reinforcement Learning

            Izzeddin Gur, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance
            08:24

            Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance

            Hongjian Wang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Soundify: Matching Sound Effects to Video
            11:48

            Soundify: Matching Sound Effects to Video

            David Chuan-En Lin, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Subgoal Search For Complex Reasoning Domains
            05:41

            Subgoal Search For Complex Reasoning Domains

            Konrad Czechowski, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Deep generative models of protein structures create new and diverse proteins
            10:58

            Deep generative models of protein structures create new and diverse proteins

            Zeming Lin, …

            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