David W. Romero

@DavidWRomero1

PhD Student - Efficient Deep Learning

Amsterdam
Vrijeme pridruživanja: listopad 2019.

Tweetovi

Blokirali ste korisnika/cu @DavidWRomero1

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @DavidWRomero1

  1. proslijedio/la je Tweet
    2. velj

    Learning Discrete Distributions by Dequantization.

    Poništi
  2. proslijedio/la je Tweet
    26. sij

    Quaternions and Euler angles are discontinuous and difficult for neural networks to learn. They show 3D rotations have continuous representations in 5D and 6D, which are more suitable for learning. i.e. regress two vectors and apply Graham-Schmidt (GS).

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    27. sij

    PDE-based Group Equivariant Convolutional Neural Networks. (arXiv:2001.09046v1 [cs.LG])

    Poništi
  4. proslijedio/la je Tweet
    26. sij

    I am thrilled to announce our paper “Feedback Recurrent AutoEncoder” was accepted at ! collaboration with Yang Yang, and Jon Ryu. . A quick thread.

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    27. sij

    Short but sweet paper on recurrent autoencoder architectures for speech compression. We systematically explore the space of RNN-AEs and show that the best method, dubbed FRAE, outperforms classical codecs by a large margin. Check it out!

    Poništi
  6. proslijedio/la je Tweet
    21. sij

    We are organizing an Workshop on Geometric and Relational Deep Learning! Registration invites will be shared soon. Interested in participating? Consider submitting an abstract or get in touch: w/

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    9. sij
    Poništi
  8. proslijedio/la je Tweet

    this very popular podcast, hear from our very own talking about Research and a wide range of machine learning topics. Thanks .

    Poništi
  9. proslijedio/la je Tweet
    10. sij

    Our work on Gauge Equivariant CNNs made it into Quanta Magazine! The article gives a nice overview on coordinate independent convolutions and connections between theoretical physics and deep learning.

    Poništi
  10. proslijedio/la je Tweet
    7. sij
    Poništi
  11. proslijedio/la je Tweet
    6. sij
    Poništi
  12. proslijedio/la je Tweet
    3. sij

    What better way to start a new year than by applying for a great tenure track position in a great city (Amsterdam) in a great team: AI systems that collaborate with people instead of replacing them: (closes in 3 days).

    Poništi
  13. proslijedio/la je Tweet
    25. lis 2019.

    Check out "Scale-Equivariant Steerable Networks" (). It is joint work with Michał Szmaja and Arnold Smeulders. We build scale-equivariant CNNs which do not use image rescaling and do not limit the admissible scale factors.

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    21. pro 2019.

    Really happy with my paper being accepted ! It describes a flexible framework for building G-CNNs that are equivariant to a large class of transformation groups. B-Spline CNNs on Lie groups:

    Poništi
  15. 22. pro 2019.

    Really exciting to have my first paper accepted at ! It provides the first group theoretical approach towards equivariant visual attention. Nice things coming up next! . Co-Attentive Equivariant Nets:

    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:

    ·