cschan

@cschan9

Associate Professor - computer vision, machine learning

Malaysia
Vrijeme pridruživanja: siječanj 2019.

Tweetovi

Blokirali ste korisnika/cu @cschan9

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @cschan9

  1. proslijedio/la je Tweet
    31. sij

    Here is another opportunity to win a travel to present your work at ! In partnership with , is hosting a computer vision for agriculture challenge.

    Poništi
  2. proslijedio/la je Tweet
    28. sij
    Poništi
  3. proslijedio/la je Tweet
    30. sij
    Poništi
  4. proslijedio/la je Tweet
    22. sij

    Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement pdf: abs:

    Poništi
  5. proslijedio/la je Tweet
    24. sij

    Well, obviously. Shutting down nuclear plants leads to more reliance and coal, oil, gas and other fossil fuel sources (even in Germany, where renewables are widely deployed), which emit...

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

    On the “Steerability” of GANs “An open secret in ML is that many models work beautifully on standard benchmarks but fail to generalize outside the lab. By ‘steering’ in latent space, we can shift the distribution while still creating realistic images.“

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

    Starting Jan 6, we're doing a series of lectures at MIT on deep learning and AI. Skip the first one, but afterwards there are some great talks (inc. , ). All are welcome. Seating limited (1st come, 1st served). Video will be posted here:

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    21. pro 2019.

    Our submission to was accepted as a spotlight, in it we try to clear up some confusion about Bayesian inference in RL, read it if you want to understand how Bayes and Bellman can get along!

    Poništi
  9. proslijedio/la je Tweet
    17. pro 2019.

    I am co-organizing MLSS-Indo 2020 in Indonesia. . Indonesia is a vast country with around 6,924,511 students but little papers in ML. I am looking for sponsors who want to support a student to attend the summerschool. Contact me if you are interested!

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

    This is the price I pay for cancelling an invited talk at a workshop on Machine Learning for Creativity and Design, when one of the organizers is an improv performer and...

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

    Capsules may replace ConvNets one day.

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

    "A Beginner's Guide to the Mathematics of Neural Networks" ... a nice gem 🙂 And *very* cool illustrations !!!

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

    Presenting "A Benchmark for Interpretability Methods in Deep Neural Networks" at poster #159 tomorrow (Dec 10th). Poster > Slides > Code > Paper > See you there! :)

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

    Stability and Generalization of Graph Convolutional Network Uniform stability needed for generalization garantees To ensure stability Sup||Eigenvalue|| must be bounded Normalized graph filters satisfy it For multi-layer GCNN BatchNorm is needed

    Poništi
  15. proslijedio/la je Tweet
    28. stu 2019.
    Poništi
  16. proslijedio/la je Tweet
    6. stu 2019.

    This is some advice I had shared with my lab on how to shorten your paper to fit the page limit. With the deadline coming up, I thought I'd share it widely.

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet

    Summarization is one of the most important & least solved tasks in Problem with all models: they are not optimized for factual correctness We introduce a new task, dataset and model. Work by Paper

    Poništi
  18. proslijedio/la je Tweet

    We celebrate the Best Paper Award at the ongoing in Seoul. Awesome SinGAN: GANs that learn from a SINGLE natural image! Kudos to & Tomer Micaeli Paper: Code: Video:

    , , i još njih 5
    Poništi
  19. proslijedio/la je Tweet
    18. lis 2019.

    Mathematics for Machine Learning. Looks like a nice companion book for machine learning and deep learning textbooks. They have a free PDF version on their website, which is nice :)

    Poništi
  20. proslijedio/la je Tweet

    My new paper is out! We show a framework in which we can both derive and gradient penalized ! We also show how to make better gradient penalties!

    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:

    ·