Kyunghyun Cho

@kchonyc

Associate Professor of Computer Science and Data Science at () & Research Scientist at

Manhattan, NY
kyunghyuncho.me
Vrijeme pridruživanja: lipanj 2009.
588 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @kchonyc

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

  1. Prikvačeni tweet
    17. lip 2019.

    80 replies 19 proslijeđenih tweetova 406 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    1. velj

    You can now apply to be an organizer for 2020 events! Please apply using the following form: . We are very excited to receive your applications! Deadline is on Feb 14th.

    41 proslijeđeni tweet 69 korisnika označava da im se sviđa
    Poništi
  3. 31. sij

    very excited to hear from Yixin about the blessings of multiple causes

    1 reply 1 proslijeđeni tweet 30 korisnika označava da im se sviđa
    Poništi
  4. 31. sij

    psyched both bc HuggingFace Transformer is going beyond text and bc this is happening with 's multimodal bitransformer

    Supervised multimodal bitransformers now available in the awesome HuggingFace Transformers library!
    7 proslijeđenih tweetova 39 korisnika označava da im se sviđa
    Poništi
  5. 30. sij

    Yanniv Romano at for math-and-data (MAD) seminar series

    11 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    24. sij

    Excited to share our latest pre-print🎉 - a framework for low-N protein engineering with data-efficient deep learning! Had a blast working with brilliant and . Thread (1/7)

    44 proslijeđena tweeta 140 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. 29. sij

    thanks leslie for having involved me in this massively fun project! learned a lot about many different algorithms, their properties and what we can learn from data using them; including BERT, k-means, GMM, cross-validation, bayesian model selection, UMAP, tSNE, PCA, ...

    New Medium article about my work w/ and on extracting representations of different senses of polysemic words from deep contextualized models like BERT, ELMo, and fastText. 👉 👈 (+ code on GitHub)
    Prikaži ovu nit
    1 reply 1 proslijeđeni tweet 31 korisnik označava da mu se sviđa
    Poništi
  8. proslijedio/la je Tweet
    29. sij

    Excited to host for an impromptu lab visit at today!

    5 replies 3 proslijeđena tweeta 99 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    28. sij

    Great talk on recent developments of unsupervised NMT at by ⁩⁦⁩

    3 proslijeđena tweeta 24 korisnika označavaju da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    29. sij

    For the first time, you can search and explore a central collection of information about clergy members who have been deemed “credibly accused” of sexual abuse by leaders of U.S. dioceses and religious orders.

    1 reply 76 proslijeđenih tweetova 82 korisnika označavaju da im se sviđa
    Poništi
  11. 29. sij

    time to ditch MNIST and embrace MNIST... wait.. no QMNIST

    Did you know QMNIST is now a part of Pytorch Torchvision.Datasets? You can use it as easily as MNIST, has 6x the test set and also comes with meta data like writer id!! 😀
    1 reply 10 proslijeđenih tweetova 50 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    28. sij

    If you're interested in becoming involved in my new project dabl , I tagged some easy first issues. Given that it's pretty early in the development, the barrier to entry should hopefully be much lower than in sklearn for example:

    10 replies 90 proslijeđenih tweetova 364 korisnika označavaju da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    28. sij

    💥 Starting the 2020 edition of 's Deep Learning class with ~200 students! 🤩 This year we *will* end up with annotated ✏️ video recordings 🎥 and publishable lecture notes 📖, as we're putting the extra effort to renew 🌟 and reorganise 🧐 the material. – mjesto: NYU Courant Institute of Mathematical Sciences

    Korisnici , i
    19 replies 196 proslijeđenih tweetova 1.081 korisnik označava da mu se sviđa
    Poništi
  14. 27. sij

    5 replies 1 proslijeđeni tweet 74 korisnika označavaju da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    25. sij

    ICYMI: 44 students were recently joined the African Master's in Machine Intelligence (AMMI) program in . AMMI is a fully funded 1 year intensive graduate program that gives young Africans training in machine learning &its applications. Full story:

    1 reply 13 proslijeđenih tweetova 29 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    25. sij

    [1/7] Super excited to present our recent work -- mBART. We demonstrate multilingual denoising pre-training produces significant gains across a variety of machine translation tasks! Joint work with

    We're releasing mBART, a new seq2seq multilingual pretraining system for machine translation across 25 languages. It gives significant improvements for document-level translation and low-resource languages. Read our paper to learn more:
    43 proslijeđena tweeta 176 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    23. sij

    Today gave a talk at Google Research Berlin about our Transformer analysis work. Met a lot of great people and feel totally happy :) Want to know details? Here are the blog posts: The Story of Heads: , Evolution of Representations:

    90 proslijeđenih tweetova 414 korisnika označava da im se sviđa
    Poništi
  18. 23. sij

    it's always a mystery why producers are fascinated by those dull-looking humanoids, but that aside, this short video clip is surprisingly informative :)

    A very nice video about our work on deep learning for breast cancer screening by and !
    Prikaži ovu nit
    5 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    23. sij

    Reminders of deadlines: Papers: abstracts due 30 Jan, papers due 6 Feb Workshops: due 14 Feb Tutorials: due 21 Feb details on each: Please submit (and circulate the calls!)

    29 proslijeđenih tweetova 81 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. 23. sij

    my social circle probably is not the most appropriate audience of this, but CDS is starting a pilot course which will be a part of the Executive Education Course program.

    3 proslijeđena tweeta 5 korisnika označava da im se sviđa
    Poništi
  21. 23. sij

    💯

    Odgovor korisniku/ci @SussilloDavid
    Oh you mean a no hidden layer deep neural network with only 1 sigmoidal output neuron? Why didn’t you just say so - instead of using obscure statistical jargon like “logistic regression?” :)
    10 korisnika označava da im se sviđa
    Poništi

@kchonyc 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:

    ·