Tweetovi

Blokirali ste korisnika/cu @hai72724774

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @hai72724774

  1. proslijedio/la je Tweet
    18. sij

    Did you know that you can write blog posts for Pages using MS Word or Google Docs, including pasting images straight into your doc, and have it all synced to GitHub and included in your blog? Here's how it's done!

    Prikaži ovu nit
    Poništi
  2. 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.

    Poništi
  3. 20. pro 2019.
    Poništi
  4. proslijedio/la je Tweet
    26. pro 2017.

    Favorite recent jupyter notebook discovery - the %debug magic: 1. Get an exception. 2. Insert a new cell, type %debug and run it. An interactive debugger will open bringing you to where the exception occurred and allowing you to look around!

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    26. ruj 2019.

    This guest lecture by was a great watch. A very thorough overview of novel techniques essential to doing deep learning well. Awesome refresher plus I picked up a couple new things that seem extremely useful!

    Poništi
  6. proslijedio/la je Tweet
    25. kol 2019.

    when it comes to language and its diversity, average humans are really bad at recall, and are not very creative. beware of this.

    Poništi
  7. proslijedio/la je Tweet
    Poništi
  8. proslijedio/la je Tweet
    9. kol 2019.

    We studied how to view optimization as sequential decision making. Examples include tree-search, greedy & gradient-style updating. We essentially learn better local decision making to better solve the overall optimization problem. (2/3)

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    7. kol 2019.

    Machine Learning is WAY more than just picking a model & calling .fit() or .train() on data It's a process... thinking about your problem in terms of correlation & features This step-by-step guide is an excellent intro to this process

    Poništi
  10. proslijedio/la je Tweet
    5. kol 2019.

    I started as an assistant professor this week at , after a 4-month wonderful visit at . My lab focuses on computational social science and natural language processing. Super excited to work with amazing colleagues and students on cool research!

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    1. kol 2019.

    . and I are excited to announce a new 3-year project funded by exploring the genealogies of online communities in and . We're looking for a new Ph.D. student + organizing interviews with moderators.

    Poništi
  12. proslijedio/la je Tweet
    15. srp 2019.

    WikiMatrix: large-scale bitext extraction from Wikipedia: 1620 language pairs in 85 languages, 135M parallel sentences, Systematic evaluation on TED With , Shuo Sun, Hongyu and Paper: Data:

    Poništi
  13. proslijedio/la je Tweet
    27. lip 2019.

    Code for our paper "What Does BERT Look At? An Analysis of BERT's Attention" () has been released!

    Poništi
  14. proslijedio/la je Tweet
    7. lip 2019.

    New work on scaling up VI to ImageNet. With Kazuki Osawa and from TokyoTech, Siddharth Swaroop and Rich Turner , and interns and Runa E. We show that VI can match Adam's performance in about the same number of epochs. 1/7

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    8. lip 2019.

    I gathered a list of influence maximization and influence learning papers in a git page for reference

    Poništi
  16. 6. lip 2019.

    Unbelievable work with so many parameters.

    Poništi
  17. 30. svi 2019.
    Poništi
  18. 13. ožu 2019.
    Poništi
  19. proslijedio/la je Tweet
    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet

    Happy that we could share progress with you all! Good Games and , and and for a great show! You can see all the details in the blog.

    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:

    ·