Sooyoung Oh

@chitchattoe

Walking in a random world

Seattle, WA
Vrijeme pridruživanja: srpanj 2009.

Tweetovi

Blokirali ste korisnika/cu @chitchattoe

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

  1. 24. velj 2018.
    Poništi
  2. proslijedio/la je Tweet
    19. velj 2018.

    I was asked to comment on the recently published Google/Verily work on predicting cardiac risk from retinal images. Nice work, nice article. Most impressed that actually has a decent crack at defining AUC in a news article.

    Poništi
  3. proslijedio/la je Tweet
    16. velj 2018.
    Poništi
  4. proslijedio/la je Tweet

    Missing data hinder replication of artificial intelligence papers. In 400 artificial intelligence papers presented at major conferences, only 6% included code, 30% included test data, & 54% included pseudocode.

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

    With the emergence of new hardware, what are the challenges for deep learning systems? We try to answer it in our TVM paper to provide reusable optimization stack for DLSys on CPU/GPU, and accelerators. I will give an oral presentation about it at

    Poništi
  6. proslijedio/la je Tweet

    I grew up in the Boston suburbs and inherited a stubborn New England refusal to acknowledge frigid temperatures.

    Poništi
  7. proslijedio/la je Tweet

    GeekWire: Time-lapse shows Seattle’s massive growth

    Poništi
  8. proslijedio/la je Tweet
    29. pro 2017.

    Recommend this clear, short piece in "What can machine learning do? Workforce implications"

    Poništi
  9. proslijedio/la je Tweet
    27. pro 2017.

    : Incredible visualisations based on simple math formulas. Via

    Poništi
  10. proslijedio/la je Tweet
    21. pro 2017.

    Vowpal Wabbit now has a companion: Neual Decision Twee

    Poništi
  11. proslijedio/la je Tweet
    21. pro 2017.

    New paper with : "Improving Generalization Performance by Switching from Adam to SGD".

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    21. pro 2017.

    When Twitter meets medical research: results from my little 'twexperiment' on Chest X-ray interpretation.

    Poništi
  13. proslijedio/la je Tweet
    21. pro 2017.

    Great blog post from on the barriers to using x-ray reports to build medical AI systems. If my last blog post was the "what", then this post addresses the "why" very well.

    Poništi
  14. proslijedio/la je Tweet
    21. pro 2017.

    We just open-sourced MUSE, our library to align embedding spaces in a supervised or unsupervised way, along with multilingual embeddings for 30 languages aligned in the same vector space, and 110 large-scale ground truth bilingual dictionaries:

    Poništi
  15. proslijedio/la je Tweet
    21. pro 2017.

    A nice summary of deep learning developments in 2017 by Eduard Tyantov. What's in store for 2018?

    Poništi
  16. proslijedio/la je Tweet
    19. pro 2017.

    Wow! I can no longer distinguish between a computer generated voice and recording of a person. Try the samples then the Turing test:

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

    Assessing image quality using Neural Networks, and further using the net to improve image quality. From Google.

    Poništi
  19. proslijedio/la je Tweet
    16. pro 2017.
    Poništi
  20. proslijedio/la je Tweet
    17. pro 2017.

    I've spent several weeks exploring the ChestXray14 dataset, and I have some serious concerns with it.

    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:

    ·