tirupal ravilla

@tirupalrao

An engineer/NLProc enthusiast. Grad student at currently. He/Him/His

Vrijeme pridruživanja: svibanj 2010.
0 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @tirupalrao

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

  1. 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
  2. proslijedio/la je Tweet
    14. sij

    By restructuring math expressions as a language, Facebook AI has developed the first neural network that uses symbolic reasoning to solve advanced mathematics problems.

    849 proslijeđenih tweetova 2.581 korisnik označava da mu se sviđa
    Poništi
  3. proslijedio/la je Tweet
    10. sij

    “Games are great models of the real world,” . “When you sit down to play or design any game, you’re testing your own intelligence and I believe games, in particular video games, are perfect test-beds for as well.” Learn more:

    2 proslijeđena tweeta 12 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    6. sij

    Professor honored with Early Career Award

    1 reply 6 proslijeđenih tweetova 51 korisnik označava da mu se sviđa
    Poništi
  5. proslijedio/la je Tweet
    29. pro 2019.

    Some people in ML share the illusion that models expressed symbolically will necessarily/magically generalise better compared to, for example, parametric model families fit on the same data. This belief seems to come from a naive understanding of mathematics 1/5

    9 replies 98 proslijeđenih tweetova 427 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    26. pro 2019.

    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

    Controversial opinion: Bayesian NNs make no sense. You only want to use Bayes rule if you have a reasonable prior of what the parameters should be. Nobody knows what is encoded by any prior over the weights of a NN. So why would we use such a prior? 1/4
    Prikaži ovu nit
    14 replies 434 proslijeđena tweeta 1.674 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    21. stu 2019.

    Exciting little update: Last year, we made the ML for Language Group (me and 's lab) carbon-neutral. This year, we expanded to the larger nine-PI CILVR Lab! (thread)

    5 replies 16 proslijeđenih tweetova 135 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    20. stu 2019.

    Tetris on the left, Snake on the right. You play both at the same time. With the same controls. You lose in one, you lose in both. Good luck.

    1.446 proslijeđenih tweetova 4.511 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    28. lis 2019.

    Excited to host at this Thursday for a talk on unsupervised cross-lingual representation learning!

    9 proslijeđenih tweetova 55 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    26. ruj 2019.

    Note: Twitter autoexpanded only one of the two links, but there are two! Reposting. ELECTRA: ALBERT:

    1 reply 14 proslijeđenih tweetova 24 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    26. ruj 2019.

    I'm still looking through the enormous number of interesting NLP submissions to , but I'm really excited to see *two* new pretraining methods that outperform XLNet/RoBERTa on NLU tasks with far fewer parameters/FLOPS:

    7 replies 76 proslijeđenih tweetova 260 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    19. ruj 2019.

    🚨🚨🚨 We just added two new features to our neural net writing app 🦄 You can now... 📕 share what you wrote via Save & Publish 📗 edit someone else's post via Duplicate & Edit Happy writing! We'll feature a few of our favorites at the bottom of

    22 proslijeđena tweeta 74 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    10. ruj 2019.

    Machine Learning for Physics and the Physics of Learning Tutorials (Schedule) - IPAM

    161 proslijeđeni tweet 475 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    10. ruj 2019.

    Cute/impressive. (From Subramanian et al.: )

    79 proslijeđenih tweetova 242 korisnika označavaju da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    23. kol 2019.

    Excited for this term's NLP speaker lineup at . If you're based at NYU or a nearby university/lab, take a look:

    5 replies 37 proslijeđenih tweetova 240 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    16. kol 2019.

    💃PyTorch-Transformers 1.1.0 is live💃 It includes RoBERTa, the transformer model from , current state-of-the-art on the SuperGLUE leaderboard! Thanks to and all the 100+ contributors!

    , , i još njih 6
    6 replies 213 proslijeđenih tweetova 688 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    20. lip 2019.

    Folks! I am finally not too embarrassed to re-release EasyGen, a visual programming language for text data pipelines for neural nets. Colab: Github: Here’s a program to scrape the web for generating Star Trek/romance book titles.

    5 replies 111 proslijeđenih tweetova 425 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    30. lip 2019.

    You should never look down on anyone unless you fully understand them. And here's the thing: you can never fully understand anyone. We all have our traumas and our dreams and our battles that no one else knows about. So stay open-minded. And be kind.

    27 replies 479 proslijeđenih tweetova 1.954 korisnika označavaju da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    30. lip 2019.

    Protip: Upload your paper to (or appropriate preprint server for the field) even if it has already been published, if you want to increase the chance of people finding (and citing) your paper. At least make sure the paper is accessible via google scholar.

    22 proslijeđena tweeta 141 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    23. lip 2019.

    Maybe our convnets will become biased towards seeing things we the way we want to see them.

    1 reply 23 proslijeđena tweeta 163 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi

@tirupalrao 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:

    ·