Asir Saeed

@the_asir

Machine Learning Engineer. Interested in NLP, Computer Vision, Japanese Literature

Meguro-ku, Tokyo
Vrijeme pridruživanja: studeni 2017.

Tweetovi

Blokirali ste korisnika/cu @the_asir

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

  1. proslijedio/la je Tweet
    10. sij

    Now that neural nets have fast implementations, a bottleneck in pipelines is tokenization: strings➡️model inputs. Welcome 🤗Tokenizers: ultra-fast & versatile tokenization led by : -encode 1GB in 20sec -BPE/byte-level-BPE/WordPiece/SentencePiece... -python/js/rust...

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

    I don't understand people who don't need coffee it's like going through life without cheat codes

    Poništi
  3. proslijedio/la je Tweet
    8. sij

    Everyone is welcome to join Asir Saeed's tutorial at Tokyo Data Science on image superresolution and other topics using fastai/PyTorch on Sat, Jan 11, 2pm-4pm Japan time at Shimbashi, Tokyo or remotely over Zoom. DM or email me (fabinger@gmail.com) for details.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    5. sij

    NLP Year in Review — 2019 An extensive list of interesting publications, creative and societal applications, tools and datasets, articles, and resources of 2019 by .

    Poništi
  5. 1. sij

    had to drive out in the middle of the night to see this but totally worth it

    Poništi
  6. proslijedio/la je Tweet
    23. pro 2019.

    New NLP News: 2020 NLP wish lists, HuggingFace + fastai, NeurIPS 2019, GPT-2 things, Machine Learning Interviews via

    Poništi
  7. proslijedio/la je Tweet
    20. pro 2019.

    Can you separately classify 3 constituent elements in a handwritten language? 🤔📝 Join the research competition today:

    Poništi
  8. proslijedio/la je Tweet
    14. pro 2019.

    ***Creative GANs for generating poems, lyrics, and metaphors*** I like to imagine that in the imagination of a GAN, most metaphors would relate-world concepts to components of a convolutional neural network.

    Prikaži ovu nit
    Poništi
  9. 15. pro 2019.

    I’m grateful that I could be part of . Looking forward to another year of making cool stuff!

    Poništi
  10. proslijedio/la je Tweet
    14. pro 2019.

    ML for the Developing World (ML4D): Quantized deep learning models on low-power edge devices for robotic systems – , Naveen Kumar, Murukesh Mohanan, , Yves Quemener, Amina Mim, [paper] [code]

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    14. pro 2019.

    Congrats to and who presented our work at NeurIPS 2019! 👏 ML for Creativity and Design: "Creative GANs for generating poems, lyrics, and metaphors" – , , [paper] [web]

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    14. pro 2019.

    The creativity workshop was a highlight of for me! Shoutout and all the others who had great work here!

    Poništi
  13. proslijedio/la je Tweet
    14. pro 2019.

    Creative GANs for generating poems, lyrics, and metaphors by , and & at Congrats to all presenters!

    Poništi
  14. 14. pro 2019.

    Thank you to everyone who stopped by! Lots of great questions!

    Poništi
  15. proslijedio/la je Tweet
    14. pro 2019.

    Will the real LeCun please stand up? Best show in town at

    Poništi
  16. 14. pro 2019.

    Yann LeCuns at the workshop 😂

    Prikaži ovu nit
    Poništi
  17. 14. pro 2019.
    Prikaži ovu nit
    Poništi
  18. 14. pro 2019.

    Checkout some of the artwork at

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    14. pro 2019.

    Today 1. Gary Marcus 2. Jeff Dean 3. Yoshua Bengio Workshop on DRL. Almost all overlapping. Gosh! 🙄 And then is presenting his poster on Machine Learning in Design and Art as well. What and where am I going? 🤨

    Poništi
  20. 14. pro 2019.

    Creativity and Design workshop starting now!

    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:

    ·