Even Oldridge

@Even_Oldridge

Sr Applied Research Scientist on the team. Focused on deep learning for RecSys and tabular data.

Vancouver, British Columbia
Vrijeme pridruživanja: siječanj 2018.

Tweetovi

Blokirali ste korisnika/cu @Even_Oldridge

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

  1. proslijedio/la je Tweet
    prije 23 sata

    I just published my first post on Medium "Is the future of Neural Networks Sparse?" . Enjoy!

    Poništi
  2. proslijedio/la je Tweet
    4. velj

    "How to do machine learning efficiently". There's so much to love about this wonderful article.

    Poništi
  3. 31. sij

    If you're running xgboost, lgbm, or other forest based models in production you need to check out our new forest inference library. 40x faster predictions, cheaper than cpu and way less rack space.

    Poništi
  4. 30. sij

    Mark's team is doing amazing work. Come help shape the future of data science and learn a ton along the way.

    Poništi
  5. proslijedio/la je Tweet
    30. sij

    This is a seriously great group to work in - very impressive results, and very innovative

    Poništi
  6. proslijedio/la je Tweet
    24. sij

    Nice example from Chris Deotte using cuML to accelerate kNN by 600x in a Kaggle kernel:

    Poništi
  7. proslijedio/la je Tweet
    20. sij

    I've blogged about my go-to tool for prediction on tabular data, CatBoost, and its differentiable (neural network based) counterpart, NODE. Future blog posts on other tools to follow!

    Poništi
  8. 16. sij

    It was such a pleasure to talk with about my love of and my work at using for tabular deep learning and RecSys.

    Poništi
  9. proslijedio/la je Tweet
    11. sij

    “Meet AdaMod: a new deep learning optimizer with memory” by Less Wright

    Poništi
  10. proslijedio/la je Tweet
    6. sij

    This is neat 😊 ✅Train a model ✅Realize you want some functionality the framework doesn't provide ✅Define said functionality in your notebook ✅🥳🎉💃 (this is using v2)

    Poništi
  11. proslijedio/la je Tweet
    4. sij

    This is one of the coolest things I've seen on in a long time. Write a bot that plays a game - and everyone's bots are constantly pitted against each other and assigned skill ratings. 🎮 Finally time to dust off AlphaGo for Kaggle 😄

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

    Evidence that GPUs can be used to accelerate deep recommender systems at inference time, great work and al!

    Poništi
  13. proslijedio/la je Tweet

    Learn how to achieve 13x speedup and 11x throughput vs CPU on Wide & Deep recommender model using Inference SDK in new blog.

    Poništi
  14. proslijedio/la je Tweet

    Vancouver artist & painter learns python to program a robotic painting arm, then learns machine learning techniques like classification & CycleGAN to train the robot to paint “good” paintings

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

    Check out NVDashboard which makes visualizing resource utilization easy when running and in JupyterLab.

    Poništi
  16. 13. pro 2019.

    Very excited to share the amazing libraries with the Vancouver data science community. Hope to see you there!

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

    I invite all my research and academia friends to apply for the Kaggle Open Data Research grant! We’re giving away $2k-$5k grants to support *your* research project and share your data and work on our public data platform

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

    A few of us are meeting up tomorrow for lunch to discuss recommender systems. RSVP in the Whova app (meetup called “recommendation systems” if you want to join.

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

    to all the people asking “who cares?” in the comment section of this video... i care! i want to work on diverse teams which hold a variety of backgrounds and perspectives.

    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:

    ·