Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Most Activation Functions Can Win the Lottery Without Excessive Depth
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-002-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-002-alpha.b-cdn.net
      • sl-yoda-v2-stream-002-beta.b-cdn.net
      • 1001562353.rsc.cdn77.org
      • 1075090661.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
            Most Activation Functions Can Win the Lottery Without Excessive Depth
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Most Activation Functions Can Win the Lottery Without Excessive Depth

            Nov 28, 2022

            Speakers

            RB

            Rebekka Burkholz

            Speaker · 0 followers

            About

            The strong lottery ticket hypothesis has highlighted the potential for training deep neural networks by pruning, which has inspired interesting practical and theoretical insights into how neural networks can represent functions. For networks with ReLU activation functions, it has been proven that a target network with depth L can be approximated by the subnetwork of a randomly initialized neural network that has double the target's depth 2L and is wider by a logarithmic factor. We show that a de…

            Organizer

            N2
            N2

            NeurIPS 2022

            Account · 952 followers

            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

            Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings
            08:49

            Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings

            Ana María Quintero-Ossa, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Uplifting Bandits
            05:04

            Uplifting Bandits

            Yu-Guan Hsieh, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Scale-invariant Learning by Physics Inversion
            04:03

            Scale-invariant Learning by Physics Inversion

            Philipp Holl, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
            03:41

            Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks

            Zhiyang Chen, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Semantic Diffusion Network for Semantic Segmentation
            04:22

            Semantic Diffusion Network for Semantic Segmentation

            Haoru Tan, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Harmonizing the Object Recognition Strategies of Deep Neural Networks with Humans
            04:06

            Harmonizing the Object Recognition Strategies of Deep Neural Networks with Humans

            Thomas Fel, …

            N2
            N2
            NeurIPS 2022 2 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 2022