AI person (Mazen)

@madebymaze

Computational Data Scientist.

Corvallis, OR
madebymaze.xyz
Vrijeme pridruživanja: listopad 2015.
400 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @madebymaze

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

  1. Prikvačeni tweet
    25. sij

    I know that I have made it when I was referenced as "AI person (Mazen)" in emails.

    1 korisnik označava da mu se sviđa
    Poništi
  2. proslijedio/la je Tweet
    prije 21 sat

    If your new algorithm for your ICML submission is too slow, this blog post is made for you:

    77 proslijeđenih tweetova 295 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    25. sij
    Odgovor korisniku/ci

    And this is the notebook

    1 proslijeđeni tweet 1 korisnik označava da mu se sviđa
    Poništi
  4. proslijedio/la je Tweet
    25. sij

    Wonderful contribution to fast_template from - there is now a `_notebooks` folder; put any notebook there, and it'll automatically be turned into a blog post using Actions. No installation required; just click and go!

    5 replies 89 proslijeđenih tweetova 348 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    24. sij
    Odgovor korisnicima

    I wrote up a blog post that I believe can help explain this behaviour. Please do let me know what you think!

    14 proslijeđenih tweetova 47 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    23. sij

    🚀 practicalAI platform launched! - A free tool to 🔍 discover & 📁 organize the top community-curated ML content. I’ll highlight a few of the major features here but be sure to check out the tutorial -

    5 replies 61 proslijeđeni tweet 193 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    18. sij

    New blog post with -- "A Sober Look at Bayesian Neural Networks": Without a good prior, Bayesian uncertainties are meaningless. We argue that BNN priors are likely quite poor, and concretely characterize one specific failure mode.

    12 replies 102 proslijeđena tweeta 432 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    20. sij

    How to ask the right question in data science projects? A new blog post where I explain the types of questions in data analysis (as laid out by & ) and the common mistakes that should be avoided. Comments and feedback are welcome.

    1 reply 15 proslijeđenih tweetova 56 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    17. sij

    اشكر على شرف تقديم هذه المحاضرة كما اشكر جميع من حضر أو شاهد البث عن بعد تجدون شرائح العرض كاملة هنا:

    أبرز محاور محاضرة "السيارات ذاتية القيادة وتحدياتها" مع: م.يحيى خوجه
    6 proslijeđenih tweetova 30 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    16. sij

    (1) Dear friends! Please help me spread the word! Proud to announce my first single author paper, a new display technology that combines optical scanning and machine learning. The results is up to x4 resolution, faster refresh rate and no more screen door effect!

    5 replies 95 proslijeđenih tweetova 331 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    16. sij

    (3) Patches are scanned using an optical scanner in my model. The method targets to improve traditional displays with local backlights by adding an optical scanner and using machine learning.

    1 reply 4 proslijeđena tweeta 10 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    14. sij

    Keep rockin' : Data Science Community Rocked by Pet Adoption Contest Cheating Scandal via

    5 proslijeđenih tweetova 5 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    14. sij

    Working at a startup forces you to be really good at handling multiple projects and prioritizing them appropriately. There are hundreds of things you can be doing and if you're not careful you'll end up with decision paralysis.

    3 proslijeđena tweeta 25 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    14. sij

    The fact that we have Data Scientists who primarily like to build models is the sign that the field is maturing. In Physics we've had a distinction between theorists and experimentalists for centuries. Einstein never collected any of his data. He built amazing models.

    9 proslijeđenih tweetova 50 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    14. sij

    I really miss doing Physics research:

    5 proslijeđenih tweetova 8 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    13. sij

    Wav2Letter@anywhere: speech recognition engine with transformer-based acoustic model. SOTA on LibriSpeech. Fast inference. Now open source.

    We have open-sourced wav2letter@anywhere, an inference framework for online speech recognition that delivers state-of-the-art performance.
    5 replies 141 proslijeđeni tweet 496 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    11. sij
    Odgovor korisnicima i sljedećem broju korisnika:

    This is a good start, but you owe it to the community to come clean completely: 1. Was PetFinder the only competition you've cheated in? 2. What were your methods and how can they be countered in the future?

    1 reply 3 proslijeđena tweeta 28 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    11. sij

    “Meet AdaMod: a new deep learning optimizer with memory” by Less Wright

    211 proslijeđenih tweetova 821 korisnik označava da mu se sviđa
    Poništi
  19. 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
  20. proslijedio/la je Tweet
    21. pro 2019.

    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

    31 reply 122 proslijeđena tweeta 675 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi

@madebymaze 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:

    ·