Piotr Nowak

@rdzeniu

Building predictive models that measure credit risk. Developing distributed, event-driven systems ~ Views are my own

Kraków, Polska
Vrijeme pridruživanja: srpanj 2011.

Tweetovi

Blokirali ste korisnika/cu @rdzeniu

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

  1. proslijedio/la je Tweet
    1. velj
    Poništi
  2. proslijedio/la je Tweet
    31. sij

    A full build of Autopilot neural networks involves 48 networks that take 70,000 GPU hours to train. Together, they output 1,000 distinct tensors (predictions) at each timestep. This is what a Tesla autopilot sees [source: ]

    Poništi
  3. proslijedio/la je Tweet
    31. sij

    Note that this is *not* just about time series and trends. It's about the much more subtle issue of "domain shift". How do you know if you have domain shift? Here's a great method, from our forthcoming book ():

    Poništi
  4. proslijedio/la je Tweet
    31. sij

    Why Random Forests can’t predict trends and how to overcome this problem. by

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

    40x faster predictions for even the deepest random forests with FIL’s new sparse forest support -

    Poništi
  6. proslijedio/la je Tweet
    26. sij

    Introduction to Anomaly Detection

    Poništi
  7. proslijedio/la je Tweet
    26. sij
    Poništi
  8. proslijedio/la je Tweet
    26. sij

    The First Article About Theoretical Data Science (and easy to read)

    Poništi
  9. proslijedio/la je Tweet

    "Needless to say, one should not even begin to trust a system like this for medical advice."

    Poništi
  10. proslijedio/la je Tweet
    26. sij

    Difference Between Standard Deviation and Standard Error in One Picture

    Poništi
  11. proslijedio/la je Tweet
    25. sij

    ML competition: identify dataset use in research articles (NLP, entity linking). Public corpus on GitHub with links to open access PDFs plus metadata for feature eng. Current TopK precision @ ~78%

    Poništi
  12. proslijedio/la je Tweet
    25. sij

    [VIDEO] for my guest lecture at is now available. "Lessons learned from building practical DL systems"

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    26. sij

    The Math Behind Bayes

    Poništi
  14. proslijedio/la je Tweet
    25. sij
    Poništi
  15. proslijedio/la je Tweet
    25. sij

    A Transfer Learning Approach to Cross-Modal Object Recognition: From Visual Observation to Robotic Haptic Exploration by Pietro Falco et al.

    Poništi
  16. proslijedio/la je Tweet
    25. sij

    Facebook has a neural network that can do advanced math

    Poništi
  17. proslijedio/la je Tweet
    24. sij

    Automated Machine Learning with Monte-Carlo Tree Search | IJCAI

    Poništi
  18. proslijedio/la je Tweet
    24. sij

    10 tools and platforms for data preparation

    Poništi
  19. proslijedio/la je Tweet
    24. sij

    Data science isn't just developing machine learning algorithms A lot of the time, you're stuck with data cleaning. What does that entail?

    Poništi
  20. proslijedio/la je Tweet
    24. sij
    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:

    ·