Eyyüb Sari

@eyyub_s

Machine Learning Research Engineer working on model compression Noah's Ark Lab. Shab Team ✌️. Views are my own.

Vrijeme pridruživanja: listopad 2010.

Tweetovi

Blokirali ste korisnika/cu @eyyub_s

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

  1. proslijedio/la je Tweet
    Prikaži ovu nit
    Poništi
  2. 13. sij

    I came to realize there is an urge to formalize processes in AI research labs at companies. Especially around source codes. We aren't programming, we are scripting. People need to realize it. That, I believe, is the root of lots of issues because we can't apply SWE processes.

    Poništi
  3. proslijedio/la je Tweet
    6. sij

    Functional programming is not esoteric, theoretical, academic, obtuse, inefficient, or inaccessible. It is simple, obvious, approachable, and elegant. Embrace it as part of your regular programming toolkit. Combine it with OO and structure. Language is secondary.

    Poništi
  4. proslijedio/la je Tweet
    31. pro 2019.
    Poništi
  5. 26. pro 2019.

    One way to see the underlying beauty of Bubble Sort is to think about it as a cheap and elegant external sort. Too bad it is slow 🤔

    Poništi
  6. proslijedio/la je Tweet
    26. ruj 2019.

    Calling all machine learning developers and data scientists 👀 Today we're excited to share the CodeSearchNet Challenge and the release of a large dataset for natural language processing and machine learning.

    Poništi
  7. proslijedio/la je Tweet
    28. kol 2019.

    Call for Proposals: Functional Conf 2019, Bengaluru – submissions close August 31!

    Poništi
  8. proslijedio/la je Tweet
    27. kol 2019.

    A my first article about was out on the blog of . It talk about how to write an API - (second, about optimization, will out soon).

    Poništi
  9. proslijedio/la je Tweet
    1. srp 2019.

    Want to play with PyTorch, but prefer OCaml to Python? Here are OCaml bindings to the PyTorch C++ API. With examples for image recognition, GANs, RL, etc. By Laurent Mazare.

    Poništi
  10. proslijedio/la je Tweet
    6. velj 2019.

    Start to talk about - Today, I tried to scan my mails with my Mr. MIME parser in . I mostly followed RFC about mails and it's time to strike my implementation with real-world.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    8. pro 2018.

    In montreal, even the garbage bins cannot escape deep learning

    Poništi
  12. proslijedio/la je Tweet
    5. pro 2018.

    At Cádiz, presented , towards a smaller and safer OS. Check it out here:

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    26. lis 2018.

    Thanks to for walking us through today at !

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet

    OH (from an awesome Lyft driver): “Today has been great. I’ve been blessed by the algorithm.” Immediately had an eerie feeling that this could become an increasingly common way to describe a day.

    Poništi
  15. proslijedio/la je Tweet
    5. velj 2018.

    Quand une boîte cherche clairement à exploiter un stagiaire.. A vomir... @jesuissnaaaail check ca.

    Poništi
  16. proslijedio/la je Tweet
    2. velj 2018.

    Meet DensePose! We introduce a new computer vision task of dense human pose estimation in the wild, which aims on mapping a RGB image of a person to 3D surface of the human body. First results are in , data and code are coming soon.

    Poništi
  17. proslijedio/la je Tweet
    1. velj 2018.

    The only thing of what we can predict about

    Poništi
  18. proslijedio/la je Tweet
    17. sij 2018.

    Standard LSTM interpretation methods qualitatively fail when dealing with compositionality (i.e. when LSTMs beat bag of words). Our new method, contextual decomposition, fixes it. Joint work with and

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    17. sij 2018.

    Bon j'ai écrit un petit article pour sur Meltdown & Spectre. Il n'y a pas vraiment de rigueur technique dans cette article dans le sens où il veut être compréhensible par tous Bisoux

    Poništi
  20. proslijedio/la je Tweet
    10. sij 2018.

    I’m thrilled to share my latest deep learning project: Turning a design mockup into code. 💻 🤖 1) Give the trained neural network a design image 2) The network converts the image into HTML markup and renders it ↴ Article: Code:

    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:

    ·