Next
Householder meets Sylvester: Normalizing Flows for Variational Inference
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Cubic-Spline Flows
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-006-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-006-alpha.b-cdn.net
      • sl-yoda-v3-stream-006-beta.b-cdn.net
      • 1375548855.rsc.cdn77.org
      • 1312734894.rsc.cdn77.org
      • Subtitles
      • Off
      • English (auto-generated)
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Cubic-Spline Flows
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Cubic-Spline Flows

            Jun 15, 2019

            Speakers

            MH

            Matt Hoffman

            Speaker · 0 followers

            About

            Invertible neural networks have been a significant thread of research in the ICML community for several years. Such transformations can offer a range of unique benefits: (1) They preserve information, allowing perfect reconstruction (up to numerical limits) and obviating the need to store hidden activations in memory for backpropagation. (2) They are often designed to track the changes in probability density that applying the transformation induces (as in normalizing flows). (3) Like autoreg…

            Organizer

            I2
            I2

            ICML 2019

            Account · 3.2k followers

            Categories

            Mathematics

            Category · 2.4k presentations

            AI & Data Science

            Category · 10.8k presentations

            About ICML 2019

            The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

            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

            Towards Semi-Automated Machine Learning
            31:16

            Towards Semi-Automated Machine Learning

            Charles Sutton

            I2
            I2
            ICML 2019 6 years ago

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

            Towards Efficient Evaluation of Risk via Herding
            14:08

            Towards Efficient Evaluation of Risk via Herding

            Zelai Xu

            I2
            I2
            ICML 2019 6 years ago

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

            A case for coded computing on elastic compute
            21:40

            A case for coded computing on elastic compute

            Markus Weimer

            I2
            I2
            ICML 2019 6 years ago

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

            Compositionality, Confidence and Crowd Modeling for Self-Driving Cars
            27:52

            Compositionality, Confidence and Crowd Modeling for Self-Driving Cars

            Sven Kreiss

            I2
            I2
            ICML 2019 6 years ago

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

            Time Series
            1:19:52

            Time Series

            Alex Smola, …

            I2
            I2
            ICML 2019 6 years ago

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

            Geoscience data and models for the climate change AI community
            11:00

            Geoscience data and models for the climate change AI community

            Karthik Mukkavilli

            I2
            I2
            ICML 2019 6 years ago

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

            Interested in talks like this? Follow ICML 2019