Další
Živý přenos začne již brzy!
Živý přenos již skončil.
Prezentace ještě nebyla nahrána!
  • title: Learning to Combine Per-Example Solutions for Neural Program Synthesis
      0:00 / 0:00
      • Nahlásit chybu
      • Nastavení
      • Playlisty
      • Záložky
      • Titulky Off
      • Rychlost přehrávání
      • Kvalita
      • Nastavení
      • Debug informace
      • Server sl-yoda-v3-stream-015-alpha.b-cdn.net
      • Velikost titulků Střední
      • Záložky
      • Server
      • sl-yoda-v3-stream-015-alpha.b-cdn.net
      • sl-yoda-v3-stream-015-beta.b-cdn.net
      • 1963568160.rsc.cdn77.org
      • 1940033649.rsc.cdn77.org
      • Titulky
      • Off
      • English
      • Rychlost přehrávání
      • Kvalita
      • Velikost titulků
      • Velké
      • Střední
      • Malé
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      Moje playlisty
        Záložky
          00:00:00
            Learning to Combine Per-Example Solutions for Neural Program Synthesis
            • Nastavení
            • Sync diff
            • Kvalita
            • Nastavení
            • Server
            • Kvalita
            • Server

            Learning to Combine Per-Example Solutions for Neural Program Synthesis

            6. prosince 2021

            Řečníci

            DS

            Disha Shrivastava

            Speaker · 0 followers

            HL

            Hugo Larochelle

            Speaker · 1 follower

            DT

            Daniel Tarlow

            Speaker · 0 followers

            O prezentaci

            The goal of program synthesis from examples is to find a computer program that is consistent with a given set of input-output examples. Most learning-based approaches try to find a program that satisfies all examples at once. Our work, by contrast, considers an approach that breaks the problem into two stages: (a) find programs that satisfy only one example, and (b) leverage these per-example solutions to yield a program that satisfies all examples. We introduce the Cross Aggregator neural netwo…

            Organizátor

            N2
            N2

            NeurIPS 2021

            Account · 1.9k followers

            O organizátorovi (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.

            Baví vás formát? Nechte SlidesLive zachytit svou akci!

            Profesionální natáčení a streamování po celém světě.

            Sdílení

            Doporučená videa

            Prezentace na podobné téma, kategorii nebo přednášejícího

            TAAC: Temporally Abstract Actor-Critic for Continuous Control
            10:44

            TAAC: Temporally Abstract Actor-Critic for Continuous Control

            Haonan Yu, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Discussion panel: Curiosity
            50:58

            Discussion panel: Curiosity

            Chelsea Finn, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Efficient Equivariant Network
            08:20

            Efficient Equivariant Network

            Lingshen He, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Oral Session 4: Vision Applications and Optimization
            1:33:58

            Oral Session 4: Vision Applications and Optimization

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training
            10:13

            Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training

            Hongwei Xue, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Self-supervised learning: What next for theory?
            31:29

            Self-supervised learning: What next for theory?

            Sanjeev Arora

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Zajímají Vás podobná videa? Sledujte NeurIPS 2021