Atul Saurav

@twtAtul

datageek, karateka, learner, survivor, husband, dad

Richmond, VA
atulsaurav.github.io
Vrijeme pridruživanja: siječanj 2010.
12 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @twtAtul

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

  1. proslijedio/la je Tweet
    1. velj

    Is there anybody out there? This account is about to rise like a phoenix from the ashes...

    15 replies 40 proslijeđenih tweetova 257 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    30. sij

    Scientific Python lecture notes

    35 proslijeđenih tweetova 91 korisnik označava da mu se sviđa
    Poništi
  3. proslijedio/la je Tweet
    30. sij

    "Always remember that to argue, and win, is to break down the reality of the person you are arguing against. It is painful to lose your reality, so be kind, even if you are right." —Haruki Murakami

    69 proslijeđenih tweetova 161 korisnik označava da mu se sviđa
    Poništi
  4. proslijedio/la je Tweet
    30. sij

    New post: a look back at Ursa Labs's work in 2019 and a look ahead our roadmap and priorities in for 2020 and beyond

    22 proslijeđena tweeta 97 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    29. sij

    The next Numba release (0.49) will be March 2020 as we do some some serious internal refactoring and cleanup. We've already deleted more than 7000 lines of code!

    1 reply 7 proslijeđenih tweetova 74 korisnika označavaju da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    30. sij

    Happy birthday !! Ten years from the first release and still young!

    26 proslijeđenih tweetova 162 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    30. sij

    We’re so excited for the milestone the pandas team has reached with the release of 1.0 today!

    62 proslijeđena tweeta 181 korisnik označava da mu se sviđa
    Poništi
  8. proslijedio/la je Tweet
    30. sij

    \o/ Great news, everybody! Pandas version 1.0 is here - Which I think means it is now ready for general use. 😉 Really happy has been able to support some of the architectural enhancements. Congrats to the whole team!

    We’re so excited for the milestone the pandas team has reached with the release of 1.0 today!
    1 reply 43 proslijeđena tweeta 178 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    30. sij

    40x faster predictions for even the deepest random forests with FIL’s new sparse forest support -

    58 proslijeđenih tweetova 224 korisnika označavaju da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    30. sij

    Did you know that Breiman published both the bagging and random forest papers *after* he retired?!? (This is from our forthcoming book: )

    15 replies 111 proslijeđenih tweetova 658 korisnika označava da im se sviđa
    Poništi
  11. 31. sij

    We already use it in Production.. looking ahead to be using dask in production sometime soon!

    I guess now that Pandas is at 1.0 we can finally use it in production ;)
    Poništi
  12. proslijedio/la je Tweet
    28. sij

    seq2seq still delivers : ) Incredible how far we've gotten in ~5 years of progress in neural conversational models, with relatively small changes. More exciting is that there's still LOTS to be done! Paper: Blog:

    54 proslijeđena tweeta 288 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    24. sij

    Meet your guide Da-Cheng! 👋 In this video series, we’ll show you a new learning framework, Neural Structured Learning! 🧠 For this week’s episode, we’ll start by coding with Python. Watch now →

    Neural Structured Learning (left), Da-Cheng (right)
    51 proslijeđeni tweet 142 korisnika označavaju da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    22. sij

    You want GAN stability without having to resort to complex architectures? It seems that my easy-to-implement "causal GAN" lead to even more stability than Relativistic GAN (see table from my old paper with new results).

    6 replies 22 proslijeđena tweeta 183 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    23. sij

    Following the tradition, I am going to share all the course material for "STAT 453: Introduction to Deep Learning and Generative Models" I am teaching this semester :)

    17 replies 243 proslijeđena tweeta 1.257 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    22. sij

    Some HIV+ patients in India are stopping medical treatment now that it is being linked to government biometric ID. Many fear being outed as LGBTQ or sex workers. This is such a depressing example of how surveillance disproportionately harms already marginalized groups.

    Odgovor korisnicima @azraism @math_rachel @ruchowdh
    Personally, not a fan of such surveillance tools. There are safer, cost-effective alternatives that don't alienate marginalized groups. e.g. many HIV patients in India have stopped accessing ART therapy since their care was linked to their Aadhaar ID:
    7 replies 162 proslijeđena tweeta 311 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    18. sij

    "Advbox: a toolbox to generate adversarial examples that fool neural networks -- " Looks like a nice, new, and comprehensive toolbox for experimenting with DL model security (github link here: )

    49 proslijeđenih tweetova 141 korisnik označava da mu se sviđa
    Poništi
  18. proslijedio/la je Tweet
    18. sij

    Papers are published online - conferences should be too!!! More attendees ($30 instead of $2000+, no visa issues) More content (anyone could stream a talk) More often ( every quarter) Seems like a no brainer Would you go to an ?

    37 replies 116 proslijeđenih tweetova 1.025 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    15. sij

    I've started to upload the videos for the Neural Nets for NLP class here: We'll be uploading the videos regularly throughout the rest of the semester, so please follow the playlist if you're interested.

    2020 edition of CMU CS11-747 "Neural Networks for NLP", is starting tomorrow! We (co-teacher and 6 wonderful TAs) restructured it a bit to be more focused on "core concepts" used across a wide variety of applications. 1/2
    Prikaži ovu nit
    82 proslijeđena tweeta 337 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    10. sij

    This is an incredible blog post talking about how to build a search engine with open-source search and ML technologies: Elasticsearch and BERT. by link: github:

    6 replies 147 proslijeđenih tweetova 492 korisnika označavaju da im se sviđa
    Poništi

@twtAtul 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:

    ·