Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Practical Real Time Recurrent Learning with a Sparse Approximation
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-013-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-013-alpha.b-cdn.net
      • sl-yoda-v3-stream-013-beta.b-cdn.net
      • 1668715672.rsc.cdn77.org
      • 1420896597.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
            Practical Real Time Recurrent Learning with a Sparse Approximation
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Practical Real Time Recurrent Learning with a Sparse Approximation

            May 3, 2021

            Speakers

            JM

            Jacob Menick

            Speaker · 0 followers

            EE

            Erich Elsen

            Speaker · 1 follower

            UE

            Utku Evci

            Speaker · 1 follower

            About

            Recurrent neural networks are usually trained with backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights "online" (after every timestep). Real Time Recurrent Learning (RTRL) eliminates the need for history storage and allows for online weight updates, but does so at the expense of computational costs that are quartic in the state size. This renders RTRL training intractable for all but the smallest networks, even ones that a…

            Organizer

            I2
            I2

            ICLR 2021

            Account · 899 followers

            Categories

            AI & Data Science

            Category · 10.8k presentations

            About ICLR 2021

            The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.

            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

            Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
            11:24

            Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

            Xavier Puig, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Feature Importance in Deep Learning Climate Emulator
            24:55

            Feature Importance in Deep Learning Climate Emulator

            Wei Xu, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
            04:36

            Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics

            Daniel Kunin, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Training a First-Order Theorem Prover from Synthetic Data
            17:21

            Training a First-Order Theorem Prover from Synthetic Data

            Vlad Firoiu, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Ditto: Fair and Robust Federated Learning Through Personalization
            10:35

            Ditto: Fair and Robust Federated Learning Through Personalization

            Tian Li, …

            I2
            I2
            ICLR 2021 4 years ago

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

            On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections
            04:55

            On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections

            Peizhao Li, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Interested in talks like this? Follow ICLR 2021