Keyulu Xu

@KeyuluXu

Machine learning PhD . Researcher , , (S20). How powerful are graph neural networks? What can neural networks reason about?

Vrijeme pridruživanja: prosinac 2019.

Tweetovi

Blokirali ste korisnika/cu @KeyuluXu

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @KeyuluXu

  1. Prikvačeni tweet
    20. pro 2019.

    Our ICLR 20 (spotlight) paper: What can neural networks reason about? Why Graph Neural Networks generalize in many reasoning tasks (e.g. physics, visual questions, graphs)? Hint: the underlying reasoning procedure resembles dynamic programming.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    14. sij

    “Can my method actually learn what I want it to learn?” Read how 's Stefanie Jegelka is applying nontraditional methods to develop more effective predictions in this month's Researcher Spotlight.

    Poništi
  3. 13. sij

    KK-ERATOは研究員のみならず、事務の秘書さんまで最強だと思う。

    Poništi
  4. 26. pro 2019.

    Our paper "What can neural networks reason about?" in 3 slides, presented at Winter Festa Episode 5 on Christmas. Great discussion with researchers from all over Japan! See Stefanie's talks for more detail (NeurIPS), (IAS)

    Poništi
  5. 20. pro 2019.

    Joint work with , S. Jegelka, K. Kawarabayashi, , . It is a follow-up of "How powerful are graph neural networks?" with , , S. Jegelka, where we answer expressive power. This work answers generalization for reasoning.

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·