rohola

@roholazandie

PhD candidate in AI , Machine learning enthusiast, NLP, Computer science and Statistics

Denver, CO
Vrijeme pridruživanja: veljača 2011.

Tweetovi

Blokirali ste korisnika/cu @roholazandie

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

  1. prije 15 sati

    وقتی دامادمون شروع کرد به یادگیری کردی بهم گفت وقتی پدربزرگ و مادربزرگتون حرف میزنن یا حتی زمانی که شما باهاشون حرف میزنید من اصلا نمیفهمم ولی وقتی شما با هم حرف میزنید میفهمم!! مرگ یا تغییر زبان های محلی ناشی از آموزش زبان دوم نیست، این نتیجه انتخاب خود ما و تلاش نکردنمونه

    Poništi
  2. 28. sij

    is one of the most important corpora in community. It's not an easy dataset to work with. Finally, I managed to write a codebase for anyone who wants to use this huge dataset to The access to a single doc is < 0.001 Github repo:

    Poništi
  3. 27. sij

    Check out the biggest simulation of the evolution of the universe to date here: It's just mind blowing.

    Poništi
  4. 17. sij

    I just wrote a code with emojis and it works perfectly! The fact that you can actually see and work with colorful inside your code is really cool! Python3.7, Ubuntu 18.06, terminal output

    Poništi
  5. 15. sij

    When you look at tensorflow codes you think to yourself: it's hard to conceptualize, there is no way to make this simpler. But when you look at pytorch version of the same code, you say: I was wrong!

    Poništi
  6. 14. sij

    آقای جمهوری اسلامی! یک عمر اعتراف گرفتی و حیثیت مخالفانت رو به زعم خودت لگد مال کردی. الان نوبت خودت شد و اعتراف کردی، مزه ش چطوره؟ دیدی چطوری آخرش رسوا و بی حیثیت شدی! این تازه اول کاره!

    Poništi
  7. proslijedio/la je Tweet

    Life is extremely fragile. It's too easy to take good health for granted.

    Poništi
  8. 4. sij

    همین هایی که رگ ملی گراییشون باد کرده اگه رییس جمهور فعلی"ایران" رو میزدن واکنششون اگر خوشحالی نبود قطعا بی تفاوتی بود!

    Poništi
  9. 3. sij

    When your bluffs last for one day!

    Poništi
  10. 28. pro 2019.

    this is probably the best talk in Really enjoyed the insightful talk by

    Poništi
  11. 22. pro 2019.

    Here is part 2 of Dirichlet distribution. I wanted to simplify the concept for myself and more importantly implement it! More about random processes will come! Nothing is hard to understand. Mathematics prevails!

    Poništi
  12. 19. pro 2019.

    I just published God doesn’t play dice! God creates dices: Dirichlet distribution (Pt.1)

    Poništi
  13. proslijedio/la je Tweet

    IMO a key to doing creative work productively is to strike a good balance b/t taking the work seriously (so you don't give up & maintain high quality standards) but not too seriously (so you're not afraid of mistakes/experiments & you're not paralyzed by the need for perfection)

    Poništi
  14. proslijedio/la je Tweet

    Best advice I ever received from one of my professors 5 years ago: “The output of your PhD is not your thesis. The output is YOU”

    Poništi
  15. 5. stu 2019.

    I hope this is just a coincidence to release this model in the 5th of Nov! They explicitly say the model can be misused in wrong ways!

    Poništi
  16. 29. lis 2019.
    Prikaži ovu nit
    Poništi
  17. 29. lis 2019.

    I implemented the julia set fractal in 2.0 and . Looks like has something to say! tf: 145.21 sec np: 165.63 sec cp: 100.06 sec

    Prikaži ovu nit
    Poništi
  18. 18. lis 2019.

    When NLP doesn't work well for NLP people 😄

    Poništi
  19. 11. lis 2019.

    A very nice read on the tools of Deep learning and the future of these technologies. The State of Machine Learning Frameworks in 2019

    Poništi
  20. proslijedio/la je Tweet

    One of the saddest things about the field of AI is how ahistorical and siloed it is. Some of the key debates of our day (e.g. innate priors vs "blank slate" minds) have been going on for many decades, across multiple fields, and deep learners have *zero* knowledge of this context

    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:

    ·