Federico Pernici

@FedPernici

Computer Vision, Machine Learning, Deep Learning, AI. Researcher

University of Florence, Italy
goo.gl/M71JT6
Vrijeme pridruživanja: rujan 2010.
50 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @FedPernici

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

  1. Prikvačeni tweet
    28. ožu 2019.

    Excited to share our recent paper about using fixed classifiers in CNN. Our approach shows that a special set of fixed classifiers generates stationary and maximally discriminative features that can be a priori “placed” in the embedding space before starting the learning process

    11 proslijeđenih tweetova 36 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    24. stu 2019.

    "I return to my meditations and the long-interrupted duty of my correspondence, and I beg your forgiveness for not having answered your last letter sooner. It is usually the case that I postpone longer than I ought the things with which I wish to take the most pains." —Leibniz

    7 replies 83 proslijeđena tweeta 505 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    31. sij

    An Opinionated Guide to ML Research: “To make breakthroughs with idea-driven research, you need to develop an exceptionally deep understanding of your subject, and a perspective that diverges from the rest of the community—some can do it, but it’s hard.”

    9 replies 237 proslijeđenih tweetova 851 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    1. velj

    Wow. Love reading these slides. Math is messy! Further, gaps in productivity may be described by one's willingness to believe your own proofs.

    "So I have decided to stop attempting to generate new mathematics, and concentrate instead on carefully checking “known” mathematics on a computer."
    1 reply 8 proslijeđenih tweetova 23 korisnika označavaju da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    22. tra 2018.

    Often overlooked: the distinction between scientist and scholar. The scientist seeks knowledge, the scholar seeks a consensus reality within a field of knowledge. It may be unfortunate that we train all scientists to be scholars, and not all scholars to be scientists.

    1 reply 12 proslijeđenih tweetova 42 korisnika označavaju da im se sviđa
    Poništi
  6. 25. sij

    The language bias issue:

    I hope not everyone in those PhD committees think like this. You are valuing quality of writing over achievements (as depicted in a CV.) You are favoring native English speakers over those whose first language is not English. Scary.
    1 korisnik označava da mu se sviđa
    Poništi
  7. 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

    13 replies 54 proslijeđena tweeta 350 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    21. sij

    The recent demo from Mobileye on a 20 min continuous session on the streets of Jerusalem is quite impressive

    4 proslijeđena tweeta 9 korisnika označava da im se sviđa
    Poništi
  9. 21. sij

    All you need is AI: China->encourage entrepreneurship and address disparities Europe->mobilize money and make it easier for investors anywhere to bring inventions to the Single Market US->restore competition so redistribution systems are not strained

    1 korisnik označava da mu se sviđa
    Poništi
  10. 20. sij

    “every key in the store matches the query to some extent. All are returned, and we take a sum, weighted by the extent to which each key matches the query”

    Poništi
  11. 19. sij

    “p(y|x,D) = \int p(y|x,w) p(w|D) dw [...] Rather than betting everything on a single hypothesis, we want to use every setting of parameters, weighted by posterior probabilities”

    Bayesian methods are *especially* compelling for deep neural networks. The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. This difference will be greatest for underspecified models like DNNs. 1/18
    Prikaži ovu nit
    1 korisnik označava da mu se sviđa
    Poništi
  12. 19. sij

    🔥🔥🔥

    1/ This shows how far the field has regressed in its understanding of probability. It's not a controversial opion, it's the opinion of someone who hasn't understood that a prior over weights in a neural network induces a prior over functions.
    Prikaži ovu nit
    2 korisnika označavaju da im se sviđa
    Poništi
  13. 16. sij

    "The idea is to synthesize a small number of data points that do not need to come from the correct data distribution, but will, when given to the learning algorithm as training data, approximate the model trained on the original data"

    1 proslijeđeni tweet 4 korisnika označavaju da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    15. sij

    Congrats to and Ali Farhadi

    16 proslijeđenih tweetova 91 korisnik označava da mu se sviđa
    Poništi
  15. proslijedio/la je Tweet
    14. sij

    This George Saunders quote captures so much of what I feel (and miss) about my few happy years as an unqualified PhD student. [Author’s Note to CivilWarLand in Bad Decline]

    1 reply 16 proslijeđenih tweetova 205 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    10. sij

    Looking to catch up on recent Continual Learning literature? I've updated the CL paper repo with NeurIPS19 and ICLR20 papers (tagged as "Just Accepted")

    13 proslijeđenih tweetova 37 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    13. sij 2018.

    "Let me interrupt your expertise with my confidence"

    13 proslijeđenih tweetova 31 korisnik označava da mu se sviđa
    Poništi
  18. proslijedio/la je Tweet
    8. sij

    This reminds me of this Flaubert paper: that gave proper credits to ULMFiT (by and ).

    i
    18 proslijeđenih tweetova 50 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    8. sij
    Odgovor korisniku/ci

    You’d think this is due to some West vs China cultural disconnect, but here’s basically the same story in 2017 featuring facial recognition tech by the Israeli firm Face-Six (you can skip straight to 2:10 in the video for the creepy comments by the CEO)

    1 proslijeđeni tweet 8 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    6. sij

    This weekend, one of Italy's main "serious" newspapers published a rant by a professor from Genoa about the terrible effects on Italian departments of having early career ERC grant winners join them.

    6 replies 20 proslijeđenih tweetova 41 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  21. proslijedio/la je Tweet
    6. sij

    Academia has a status problem. "You didn't study at Cambridge? You don't work for an Ivy League uni? Then you're nothing." If anything, those who achieve at lower ranked unis are the real stars because they've succeeded despite fewer resources.

    100 replies 750 proslijeđenih tweetova 5.968 korisnika označava da im se sviđa
    Poništi

@FedPernici još nije objavio nijedan Tweet.

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:

    ·