Shahab Bakhtiari

@ShahabBakht

postdoc in computational neuroscience and machine learning at Mila - McGill || exploring representations in brains and machines

Montreal, Canada
Vrijeme pridruživanja: travanj 2013.

Tweetovi

Blokirali ste korisnika/cu @ShahabBakht

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

  1. Prikvačeni tweet
    7. stu 2019.

    Check out our paper: “Influence of stimulus complexity on the specificity of visual perceptual learning” This was part of my PhD work in Chris Pack’s lab

    Poništi
  2. proslijedio/la je Tweet
    12. sij

    Sadly, no measure will bring back the loved ones lost. Personally, taking actions has always helped me cope with darker times. If you are the same, please consider joining us in donating to the scholarship fund set by in memory of students in (Link below)

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

    A sad day. Preliminary conclusions of internal investigation by Armed Forces: Human error at time of crisis caused by US adventurism led to disaster Our profound regrets, apologies and condolences to our people, to the families of all victims, and to other affected nations. 💔

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

    Targeting cultural sites for destruction is a war crime.

    Poništi
  5. proslijedio/la je Tweet

    Our message to . I hope he hears it. Part 1/3 “Chuck Schumer had been consistently hawkish on Iran. He has refused to call out Trump’s actions despite our constant pleas.”

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    1. sij

    1/ I have been following the spirited discussion about the brain, action, and thought by , , , and others. Much of what I have to say in the following thread is no doubt self-evident to many but I thought it might be worth going over anyway.

    Prikaži ovu nit
    Poništi
  7. 29. pro 2019.
    Poništi
  8. proslijedio/la je Tweet
    29. pro 2019.
    Odgovor korisnicima i sljedećem broju korisnika:

    Thanks for the shout-out! We're preparing our first to be released in January, which will list The IBL, authorA, authorB, ... authorZ plus a long contribution statement in the supplement

    Poništi
  9. proslijedio/la je Tweet

    Understanding the computational principles underlying artificial deep neural networks is likely a prerequisite for understanding the computational principles underlying biological brains.

    Poništi
  10. 26. pro 2019.

    The experiments in this paper are brilliant, but what is more brilliant is the decade long team effort put into running these difficult experiments.

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

    Two papers accepted to ICLR 2020 -- a festivus miracle! Recurrent neural circuits for contour detection Disentangling neural mechanisms for perceptual grouping (Spotlight) With JK Kim, , Alekh Ashok, and 1/17

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

    Sick and tired of holiday fun? A cure: our paper on V1! (and for the image: apologies to Jorge Cham )

    Poništi
  13. 21. pro 2019.

    Great discussion points! For many of them, I would be somewhere in the middle.

    Poništi
  14. 20. pro 2019.

    re "which sensory system is more important?" try this experiment: Tie your shoelaces eyes close vs eyes open but with gloves! A better version of the 2nd condition would be with lidocaine but didn't have any at home.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    19. pro 2019.

    It's the holiday season, and as always, my lab did our awkward Xmas family photos for the year. Once again, all I can really say is: 👌

    Poništi
  16. proslijedio/la je Tweet

    Folks, these are JAX examples in Colab notebooks that YOU can just run right now and get a machine with 8 TPU accelerators working for YOU! 🚤🚄🔥⚡️🏃‍♂️🏃‍♀️ 👇👇👇

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet

    Peering into a deep network trained on retina data: - Instantaneous RFs are context-dependent and state-based - Network subspace used by white noise and natural scenes are different [Nice update from ]

    Poništi
  18. 18. pro 2019.

    On the false belief that a specific approach is crowding out other approaches/methods/papers in a field

    Poništi
  19. proslijedio/la je Tweet
    Poništi
  20. 16. pro 2019.

    So many open questions! Just the pattern of direction selectivity across cortical layers and areas can entertain me for a while: L4 neurons have the highest direction selectivity in all the visual areas!!

    Prikaži ovu nit
    Poništi
  21. 16. pro 2019.

    A physiological survey of mouse visual cortex from

    Prikaži ovu nit
    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:

    ·