Tom Brown

@nottombrown

AI research . Previously breaking neural nets .

SF
Vrijeme pridruživanja: lipanj 2009.

Medijski sadržaj

  1. 24. sij
    Odgovor korisniku/ci

    Reviewer 2: This paper is clear and thorough, but it unfortunately failed to trigger my $$\sum$$ receptor. Author: We thank Reviewer 2 for their feedback and have copy pasted the definition of AdaBoost into our paper.

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  2. 14. sij

    For the last few months, has been turning my phone into a fancy 3D scanner. Now lets you edit scans too I have a strange love of remixed classical sculptures, and this is one step closer to making my own. HT

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
    Prikaži ovu nit
  3. 3. sij
    Odgovor korisnicima

    12/17. This is hard.

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  4. 27. pro 2019.

    In 1944, the CIA distributed a Simple Sabotage Field Manual with instructions for discretely making organizations less effective. Useful lens for noticing where organizations can become unintentionally self-sabotaging. HT

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
    Prikaži ovu nit
  5. 25. stu 2019.

    - curious what you've been reading lately :)

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  6. 4. lis 2019.

    Stuart Russell points to fossil-fuel mega-corporations as examples of powerful and misaligned entities that we built. Corporations were designed to maximize shareholder value, but in this case they worked to outsmart and manipulate the rest of humanity.

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  7. 4. lis 2019.

    Yoshua Bengio working hard to moderate an impromptu debate on AI value alignment on 's FB wall. Fascinating thread.

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  8. 25. ruj 2019.
    Odgovor korisniku/ci
    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  9. 15. ruj 2019.

    Ah, Aristarchus used the half moon to figure out the relative distance!

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  10. 15. ruj 2019.

    This lit review from points out three core questions in progress studies. Fields can be defined by their questions or by the tools used to answer questions. Curious what tools will be developed to answer these questions on progress.

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  11. 22. kol 2019.

    Most adversarial robustness work focuses on the L_inf and L_2 perturbation attacks (red box in the grid below). The new UAR metric lets researchers test their defenses on a much wider range of attacks and see which defenses give broad benefits and which do not. 1/

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
    Prikaži ovu nit
  12. 12. kol 2019.
    Odgovor korisniku/ci
    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  13. 11. kol 2019.

    's new "AI thought leadership certification service" is excellent HOWEVER the bronze and gold medals look similar and now I don't know whether to follow the thoughts of Bengio or Brundage. Plz advise.

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  14. 1. kol 2019.

    Learning Day fills my heart with green fluorescent joy. 💚📗🍏💚

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  15. 30. srp 2019.

    (3/4) Downside of ratchet approach is some designs can't be reached via small incremental changes. Also hard to know *which* tiny code changes to make. This is where understanding under/overfitting, regularization etc is useful. See 's talk:

    Prikaži ovu nit
  16. 10. srp 2019.

    Why the AI community needs to cooperate on safety from et al. Concrete examples of how AI development might go wrong, plus a more general analysis of where/when we might expect market failures. I love concrete examples.

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  17. 16. velj 2019.
    Odgovor korisniku/ci

    This type of reproducibility work is difficult and valuable for the community. Thanks for contributing. In the original CIFAR10 paper the overfitting was worse for older results (shown below). Do you have a theory for why we don't see that for ImageNet models?

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
  18. 13. ruj 2018.

    At least for a human, this isn't a tricky task. We tried to make it as easy as possible. For example, we only count confident errors as mistakes, and we don't allow any ambiguous birds and bicycles (ie. we don't allow things like this bird riding a bicycle).

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
    Prikaži ovu nit
  19. 13. ruj 2018.

    Astonishingly, no known machine learning system can reliably tell a *bird* from a *bicycle* when there’s an adversary involved. My colleagues and I have proposed a contest to see if we can change this.

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
    Prikaži ovu nit
  20. 24. kol 2018.

    Trick #3: They add a face-specific GAN to touch up the face after the main generation is finished. They include an ablation study and it looks like it helps substantially.

    Prikaži ovu nit

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:

    ·