Tweetovi

Blokirali ste korisnika/cu @punit_haria

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

  1. proslijedio/la je Tweet

    Mathematicians think in proofs, lawyers in constructs, logicians in operators, dancers in movement, artists in impressions, drummers in rythms, and idiots in labels. Bed of Procrustes.

    Poništi
  2. proslijedio/la je Tweet
    31. sij

    The bar is not as high as you think. You can: - get that job - meet that person - start that company But because you think the bar's so high, you won't even try. Which is why the bar’s so low!

    Poništi
  3. proslijedio/la je Tweet
    25. sij

    I'll use comic sans throughout my entire thesis defense if this tweet gets 100 retweets.

    Poništi
  4. proslijedio/la je Tweet
    13. sij

    Ramanujan’s first letter to G.H. Hardy reminds me of the difficulties faced by independent, often self-taught researchers working their way into the scientific research community.

    Poništi
  5. proslijedio/la je Tweet
    8. sij

    A good listing of tricks for ML research. Probably combining any two of these could get you a paper at a conference. Please don't do that blindly. Slide by .

    Poništi
  6. proslijedio/la je Tweet
    8. sij

    If 1024 fair coins are each tossed 10 times, chances are good (> 63%) that at least one will come up heads 10 times in a row; and that coin will be proud to explain how its skill, faith, guts & determination made its achievement possible, and how that combo can work for you too.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    12. pro 2019.

    Today, Latent Logic becomes part of Waymo. Their uniquely talented team, based in Oxford, UK, uses imitation learning to simulate realistic models of human behavior on the road—key to developing safe self-driving vehicles.

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet

    Refreshingly honest take on hype cycle around the Neural ODE paper by one of authors presented this year at , which won a best paper award at last year. Video:

    Poništi
  9. proslijedio/la je Tweet
    6. pro 2019.

    Looking for something to read in your flight to ? Read about Normalizing Flows from our extensive review paper (also with new insights on how to think about and derive new flows) with

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet

    data scientist: how can I help? them: I’d love if you could take a look at my data data scientist: sure. tell me about the dataset them: ok. but first. are you in the right headspace to receive information that could possibly hurt you?

    Poništi
  11. proslijedio/la je Tweet
    5. pro 2019.

    Two important lessons I learned in my twenties: - If you think everyone hates you, you probably need to sleep. - If you think you hate everyone, you probably need to eat.

    Poništi
  12. proslijedio/la je Tweet

    If you don't have empathy with animals, you don't have empathy.

    Poništi
  13. proslijedio/la je Tweet
    8. ožu 2019.

    Guy at next table in coffee shop: "What are you working on so intensely, Miss?" Me: Writing a book." Him: "What's it about?" Me: "Artificial intelligence." Him: "Did you know that two AIs at Facebook invented their own language that humans couldn't understand?" Me: uh....

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet

    For context on Manafort’s 47 months in prison, my client yesterday was offered 36-72 months in prison for stealing $100 worth of quarters from a residential laundry room.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet

    >>> a = np.zeros(5, 5) >>> TypeError: data type not understood # thanks numpy, that's very helpful. pretty sure if isinstance(dtype, int): print("did you mean to use a tuple for size?") would have saved the human race a gajillion hours.

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet

    When we're sharing information, my heart feels like it's on FHIR.

    Poništi
  17. proslijedio/la je Tweet
    13. velj 2019.

    So after training 7 days on our photobooth images here is the mandatory interpolation video. Looks like it handles the transitions from singleface to multiface sequences a bit better the pro-GAN ... Still have to play with stylemixing now!

    Poništi
  18. proslijedio/la je Tweet
    8. velj 2019.

    What are the most exciting topics and developments in ML for you at the moment? Why?

    Poništi
  19. proslijedio/la je Tweet
    20. sij 2019.

    Science is representation learning by humans. Deep learning is representation learning by machines. See slide (w/ references) from lecture on deep learning basics:

    Poništi
  20. proslijedio/la je Tweet
    15. sij 2019.

    How to generate high-quality speech from a new speaker in 5-10 minutes with few-shot meta-learning. Check out the samples here: Arxiv:

    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:

    ·