Amlan Kar

@amlankar95

PhD Student in the Machine Learning group /. Research Scientist . Previously .

Toronto, Ontario
cs.toronto.edu/~amlan/
Vrijeme pridruživanja: ožujak 2018.
6 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @amlankar95

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @amlankar95

  1. Prikvačeni tweet
    22. srp 2019.

    Accepted as an oral at ICCV 2019! :)

    Excited to release our work on MetaSim which learns to generate synthetic datasets that resemble real datasets in content. Antonio Torralba etc paper: project page:
    Prikaži ovu nit
    18 proslijeđenih tweetova 146 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    23. sij

    Congrats to my amazing PhD student for being one of five recipients of the Microsoft Ade Lovelace Fellowship! Very proud of you David!

    Extremely proud of being one of the recipients of the 2020 Microsoft Ada Lovelace Fellowship.
    1 proslijeđeni tweet 42 korisnika označavaju da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    18. sij

    If you draw lines through vertices of a pentagram, and draw lines between the new points you get that way, and so on, you can get an infinity of pentagrams - all rescaled by different powers of the golden ratio! This picture was drawn by James Dolan using Mathematica. (1/n)

    10 replies 91 proslijeđeni tweet 341 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    14. sij

    Exciting start of the year for theory of ! SGD on neural nets can: 1) simulate any other learning alg w. some poly-time init [Abbe & Sandon ] 2) learn efficiently hierarchical concept classes [ & Y. Li ]

    1 reply 45 proslijeđenih tweetova 172 korisnika označavaju da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    11. sij

    Current image datasets are getting very large and pre-training on them is time consuming. We are releasing Neural Data Server (NDS), a search engine for transfer learning data! Webservice: Paper:

    163 proslijeđena tweeta 645 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    10. sij

    Reality and simulation converging...

    0:29
    I have added some dynamic lighting to my VR Train scene. All made inside and rendered with
    Prikaži ovu nit
    5 replies 32 proslijeđena tweeta 232 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    12. velj 2019.

    How do you get a Union Minister to tweet what you want? Well, you go and edit the trending document made by BJP IT cell, and then you control what they tweet. Thread. Here's the video of this morning when their trending document got automagically updated :-) 1/n

    888 replies 9.445 proslijeđenih tweetova 13.433 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    26. pro 2019.

    I realize everyone's twitter feed looks different. But I'll go ahead and subtweet two conversations that I see going by right now: a) How the heck did Shopify get so big this decade and b) You have to work 80 hours a week to be successful. Thread/

    5.854 proslijeđena tweeta 19.248 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    25. pro 2019.

    Rephrasing with my own words: DL is a collection of tools to build complex modular differentiable functions. These tools are devoid of meaning, it is pointless to discuss what DL can or cannot do. What gives meaning to it is how it is trained and how the data is fed to it

    14 replies 90 proslijeđenih tweetova 466 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    20. pro 2019.

    + + more this Sunday on

    4.317 replies 17.603 proslijeđena tweeta 42.723 korisnika označavaju da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    26. stu 2019.

    Write LaTeX in Slack! After I ironed out the last bugs, my browser plug-in was just accepted at the addon stores. It works like a charm and is a great tool for collaborating on papers! Firefox: Chrome:

    1 reply 11 proslijeđenih tweetova 28 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    23. pro 2019.

    The first four presenters in the session today are all female researchers. Somehow India has found a solution (or removed an obstacle) that other countries have not discovered! The ratio of female presenters is around 40%, and similarly for the attendees!

    1 reply 10 proslijeđenih tweetova 50 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    18. pro 2019.

    Introducing Generative Teaching Networks - they generate synthetic data optimized to train learners as fast as possible - a new way to generate data for architecture search & more! Led by w/ , , &

    1 reply 22 proslijeđena tweeta 86 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    14. pro 2019.

    “It’s possible that the author has a different upbringing than you do. It’s possible that the example on the screen doesn’t match your experience. It’s possible that you don’t like someone’s politics, but they’re currently doing something interesting…”

    4 proslijeđena tweeta 35 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    13. pro 2019.

    Want a sneak peak for what's next with Neural ODEs? I will be talking about Higher Order Autodiff in JAX. Work with , , and ! Program Transformations: Sat. 14, Room West 114 Poster: 12-14:00 Talk: 17:00-17:20

    6 replies 64 proslijeđena tweeta 320 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    10. pro 2019.

    Come and see our Toronto Annotation suite -- annotation powered with A.I. -- demo today at NeurIPS!

    We'll be demoing the first version of the Toronto Annotation Suite () today at ! Come talk to us at 5:30 PM today at East Exhibition Hall B+C to find out more about cool stuff in AI assisted data labeling and management!
    1 reply 12 proslijeđenih tweetova 91 korisnik označava da mu se sviđa
    Poništi
  17. 10. pro 2019.

    We'll be demoing the first version of the Toronto Annotation Suite () today at ! Come talk to us at 5:30 PM today at East Exhibition Hall B+C to find out more about cool stuff in AI assisted data labeling and management!

    Korisnici , i
    7 proslijeđenih tweetova 43 korisnika označavaju da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    8. pro 2019.

    if y'all r lookin for somethin to read while walking around Vancouver, check out my newest paper: "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One" with

    35 proslijeđenih tweetova 160 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    6. pro 2019.

    After a ton of work by a bunch of people, we're releasing an entirely new Neural Tangents. Paper: Github: Colab Notebook:

    5 replies 130 proslijeđenih tweetova 500 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    5. pro 2019.

    Over the past 5 months we’ve been experimenting how to steer a mammoth without training it. Here is how.

    6 replies 112 proslijeđenih tweetova 386 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  21. proslijedio/la je Tweet
    3. pro 2019.

    This 4-page zinger by argues that computer scientists often do harm by relying on naive, vague, and technology-centric notions of "social good". It has the most punchy introduction of any paper I've read.

    10 replies 149 proslijeđenih tweetova 466 korisnika označava da im se sviđa
    Poništi

@amlankar95 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:

    ·