elvis

@omarsar0

Education | Research Scientist | Science Communicator and Educator | Ph.D. (NLP and Machine Learning) | Editor | 👶(my 4yr old)

Amsterdam, The Netherlands
linkedin.com/in/omarsar/
Vrijeme pridruživanja: rujan 2015.
565 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @omarsar0

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @omarsar0

  1. Prikvačeni tweet
    2. velj

    📰 NLP Newsletter #3: Flax, Thinc, Language-specific BERT models, Meena, Flyte, LaserTagger,…📰 featuring: , , , , , , , ,. GitHub: Medium:

    88 proslijeđenih tweetova 336 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    prije 23 sata

    Guest blog post from angel investor on sparse tensors in neural nets. I am VERY excited by what's going to happen in sparsity-land this year 🔥

    38 proslijeđenih tweetova 182 korisnika označavaju da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    2. velj

    📰 NLP Newsletter #3: Flax, Thinc, Language-specific BERT models, Meena, Flyte, LaserTagger,…📰 featuring: , , , , , , , ,. GitHub: Medium:

    88 proslijeđenih tweetova 336 korisnika označava da im se sviđa
    Poništi
  4. 2. velj

    A great opportunity to work on an NLP project 👇

    Turkish-: Anyone interested in a Turkish BERT and wants to evaluate it on downstream tasks? I did evaluation only for UD PoS tagging - any help is really appreciated! Would really like to have a proper evaluation before adding it to the Transformers hub🤗
    Prikaži ovu nit
    1 proslijeđeni tweet 2 korisnika označavaju da im se sviđa
    Poništi
  5. 2. velj

    👶 is seriously interested in space stuff 🪐 we tried giving him cough medicines using all the tricks in the book, nothing worked I came up with this idea: I asked him to pretend he was a black hole and that the medicine was just space junk that can be swallowed... it 💯 works!

    14 korisnika označava da im se sviđa
    Poništi
  6. 2. velj

    I reposted a Twitter thread (in the form of a blog post) containing some ML and NLP books I had recommended a month ago. Happy learning!

    This is a list of my top 10 book recommendations for learning the nitty-gritty of NLP and ML by
    2 proslijeđena tweeta 16 korisnika označava da im se sviđa
    Poništi
  7. 1. velj

    It's important to understand that going too fast only for the metrics is only going to feel good at the moment but the consequences are just bad. I would encourage the same not only for publishing but learning and life in general.

    The field is already self-correcting. Good departments/labs are clearing their eyes, caring less about paper count, seeing through the noise. Don't worry so much about the ICML deadline. Slow down, relax, try to do work you're proud of, submit when it's ready.
    2 proslijeđena tweeta 9 korisnika označava da im se sviđa
    Poništi
  8. 1. velj

    Arabic BERT 👏

    Way to go! Very happy to see the Arabic version of Bert.
    4 korisnika označavaju da im se sviđa
    Poništi
  9. 31. sij

    And the sooner I realize the less I know the more I want to learn. Circle of learning.

    The more I learn, the less I know. I've accepted this, and am now just enjoying the ride.
    6 korisnika označava da im se sviđa
    Poništi
  10. 31. sij

    I used Kibana since the early days. I am excited to see how it has evolved in the past years. It was voted #1 monitoring tool of 2019. That's the work of open-source and the community working towards building the best tool for observability. cc:

    4 proslijeđena tweeta 15 korisnika označava da im se sviđa
    Poništi
  11. 30. sij

    Oh really!? That's sweet! Welcome to this wonderful community.

    We're standardizing OpenAI's deep learning framework on PyTorch to increase our research productivity at scale on GPUs (and have just released a PyTorch version of Spinning Up in Deep RL):
    2 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Poništi
  12. 30. sij

    "A curriculum makes learning difficult things easier and approachable for us humans. But, how about machine learning models? Can we train our models more efficiently with a curriculum? Can we design a curriculum to speed up learning..."

    Humans learn from curriculum since birth. We can learn complicated math problems because we have accumulated enough prior knowledge. This could be true for training a ML/RL model as well. Let see how curriculum can help an RL agent learn:
    Prikaži ovu nit
    3 korisnika označavaju da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    29. sij

    We're assembling a new UI team at ! Looking for a Product Designer and JavaScript Engineer to help us build Kibana. Many projects lined up, distributed team, great benefits 📊💻📡

    1 reply 8 proslijeđenih tweetova 10 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. 30. sij

    This year I am keen on featuring ML and NLP tools and projects in the NLP Newsletter. They help to inspire other developers and also promote some of the interesting ideas coming from NLP and ML. Reach out if you are working on something interesting and would like to feature it.

    1 reply 6 proslijeđenih tweetova 31 korisnik označava da mu se sviđa
    Poništi
  15. 30. sij

    everyone: "the funny thing is..." me: *still waiting for the funny part* it's actually funny/interesting how people use language... maybe people mean "interesting" instead of "funny" 🤔

    1 reply
    Poništi
  16. 29. sij

    What are your favorite sources for keeping up to date with ML and NLP?

    5 replies 4 proslijeđena tweeta 28 korisnika označava da im se sviđa
    Poništi
  17. 28. sij

    Actually, I kinda ready it already but I am into interdisciplinary works so a second round won't hurt

    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. 28. sij

    I know what my next paper to read is👇

    *Our paper diagnosing problems in fair ML now on arXiv!* . Took a few weeks, b/c our interdisciplinary collaboration broke the paper categorization system. 😂
    Prikaži ovu nit
    1 reply 2 proslijeđena tweeta 5 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    27. sij

    New NLP News: NLP Progress, Restrospectives and look ahead, New NLP courses, Independent research initiatives, Interviews, Lots of resources (via )

    1 reply 122 proslijeđena tweeta 369 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    23. sij

    BETO: Spanish BERT

    20 proslijeđenih tweetova 18 korisnika označava da im se sviđa
    Poništi

@omarsar0 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:

    ·