Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-014-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-014-alpha.b-cdn.net
      • sl-yoda-v3-stream-014-beta.b-cdn.net
      • 1978117156.rsc.cdn77.org
      • 1243944885.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
            On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning

            May 3, 2021

            Speakers

            RW

            Ren Wang

            Speaker · 0 followers

            KX

            Kaidi Xu

            Speaker · 0 followers

            SL

            Sijia Liu

            Speaker · 0 followers

            About

            Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. It enables us to learn a $\textit{meta-initialization}$ of model parameters (that we call $\textit{meta-model}$) to rapidly adapt to new tasks using a small amount of labeled training data. Despite the generalization power of the meta-model, it remains elusive that how $\textit{adversarial robustness}$ can be maintained by MAML in few-shot learning. In addition to generali…

            Organizer

            I2
            I2

            ICLR 2021

            Account · 888 followers

            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

            Panel: Probabilistic vs. Non-Probabilistic Approaches to EBMs
            1:05:33

            Panel: Probabilistic vs. Non-Probabilistic Approaches to EBMs

            Yann LeCun, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%

            Domain-Robust Visual Imitation Learning with Mutual Information Constraints
            04:51

            Domain-Robust Visual Imitation Learning with Mutual Information Constraints

            Edoardo Cetin, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Adder Neural Networks
            34:17

            Adder Neural Networks

            Yunhe Wang

            I2
            I2
            ICLR 2021 4 years ago

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

            Meta-Learning of Structured Task Distributions
            05:18

            Meta-Learning of Structured Task Distributions

            Sreejan Kumar, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Generalization in data driven models of primary visual cortex
            09:14

            Generalization in data driven models of primary visual cortex

            Konstantin-Klemens Lurz, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Conditional Coding for Flexible Learned Video Compression
            04:53

            Conditional Coding for Flexible Learned Video Compression

            Théo Ladune, …

            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