Tim Davidson

@im_td

ML | variational neurons enthusiast | alumn | mostly tweet about AI and some wild thoughts

Vrijeme pridruživanja: svibanj 2015.

Tweetovi

Blokirali ste korisnika/cu @im_td

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

  1. Prikvačeni tweet
    8. ožu 2019.

    Thrilled to finally share our work 'Reparameterizing Distributions on Lie Groups' w/ +Patrick Forré was accepted at as an Oral! 🌍  TL;DR: Reparameterize distributions on arbitrary Lie group, non-invertible normalizing flow.

    Poništi
  2. prije 9 sati

    would be great to see this normalized by endowment/funding

    Poništi
  3. proslijedio/la je Tweet
    6. velj

    All things in moderation, especially etymology

    Poništi
  4. 3. velj

    that conclusion doesn't quite feel like a 'merely' though

    Poništi
  5. 3. velj
    Poništi
  6. proslijedio/la je Tweet
    31. sij

    Very excited to share "Learning Discrete Distributions by Dequantization" () in collaboration with and , from my internship at . We explore different methods and distributions for dequantization and reach 3.06 bpd on CIFAR10.

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

    A friend just sent me this excerpt from a Tesla blog I wrote 14 years ago

    Poništi
  8. proslijedio/la je Tweet
    29. sij

    The next decades are going to be very interesting as machine learning for robotics *really* starts to positively impact our economy. Congrats to for this launch, and robotics friends , , for pushing the envelope.

    Poništi
  9. proslijedio/la je Tweet
    28. sij

    That's such a nice idea: a proposal for standardized reporting within publications on the carbon costs of producing/presenting the science. Transparency is the first step!

    Poništi
  10. proslijedio/la je Tweet

    The cental rule in life is that it is much, much better to panic early than late.

    Poništi
  11. proslijedio/la je Tweet
    26. sij
    Odgovor korisniku/ci

    Interesting paper on manifold valued regression. The proposed solution is equivalent to that found in the Homeomorphic VAE paper of , and (-> Eq. 33)

    Poništi
  12. proslijedio/la je Tweet
    24. sij

    Check out the new release of NumPyro . This includes an implementation of 's Block Neural Autoregressive Flow in JAX and its usage in MCMC. Also, let us know what you think about the new Sample Adaptive MCMC sampler.

    Poništi
  13. proslijedio/la je Tweet
    22. sij

    I see many papers that begin with a sentence equivalent to "Topic X is popular". Popularity is not a sound scientific reason for studying a topic, so such opening sentences strike me as lame. How about "This paper shows how to solve issue Y with method M for X"? 1/2

    Prikaži ovu nit
    Poništi
  14. 22. sij
    Poništi
  15. proslijedio/la je Tweet
    21. sij
    Poništi
  16. 21. sij
    Poništi
  17. 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
  18. proslijedio/la je Tweet

    Random thought: Articles on should stop focusing on futuristic self-driving trolley cars as examples (which still need years) and instead put more focus on existing concerning real-world use cases such as COMPAS and PredPol. It would help raise awareness of awful AI❗

    Poništi
  19. proslijedio/la je Tweet
    2. sij

    Congrats to Google, but let’s not forgot the team from NYU who last year published better results, validated on more cases, tested on more readers, and made their code and data available. They just don’t have the PR machine to raise awareness.

    Prikaži ovu nit
    Poništi
  20. 3. sij

    the world is literally burning - not figuratively, literally.

    Poništi
  21. 24. pro 2019.

    it's a shame we don't have a better way of measuring 'contribution', then # papers submitted and # papers accepted .. how many/which of these matter..?

    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:

    ·