Tweetovi

Blokirali ste korisnika/cu @alexis_b_cook

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

  1. Prikvačeni tweet
    7. sij

    is hiring a data science educator!

    Poništi
  2. proslijedio/la je Tweet
    5. velj

    What’s a quick read (<1hr), in any format, that either changed your life or is something you’d recommend to everyone?

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    31. sij

    Congrats ! Have you taken a Kaggle Learn course? Share your certificate with us!

    Poništi
  4. 29. sij

    Also how I learned (and then later mostly forgot) Bayesian nonparametrics

    Poništi
  5. proslijedio/la je Tweet
    25. sij

    Exploring the cost of living with a little and . I need to make more use of excellent geospatial analysis course.

    Poništi
  6. proslijedio/la je Tweet
    21. sij

    Highly recommend 's Machine Learning Explainability course. One of the many gems in this course is the tutorial on SHAP and the accompanying code. Its a brief set of tutorials in notebooks, but very worthwhile:

    Prikaži ovu nit
    Poništi
  7. 9. sij

    An encouraging story for people trying to break into machine learning. You'll experience successes, and you'll also know failure. It's important to keep moving (so that idea didn't work? try another one!). Collaborate with people with similar goals.

    Poništi
  8. 3. sij

    TIL never to merge to master late on Friday afternoon ... even when the unit tests pass ...

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

    We're releasing "Dota 2 with Large Scale Deep Reinforcement Learning", a scientific paper analyzing our findings from our 3-year Dota project: One highlight — we trained a new agent, Rerun, which has a 98% win rate vs the version that beat .

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

    Hiring a data scientist at Kaggle!

    Poništi
  12. 3. pro 2019.

    amazing how easy it is to get started! $ pip install procgen $ python -m procgen.interactive --env-name starpilot usage: [--env-name {bigfish,bossfight,caveflyer,chaser,climber,coinrun,dodgeball,fruitbot,heist,jumper,leaper,maze,miner,ninja,plunder,starpilot}]

    Poništi
  13. proslijedio/la je Tweet
    29. lis 2019.

    Learning to Predict Without Looking Ahead: World Models Without Forward Prediction Rather than hardcoding forward prediction, we try to get agents to *learn* that they need to predict the future. Check out our paper!

    Prikaži ovu nit
    Poništi
  14. 8. lis 2019.

    Announcing Kaggle's newest course -- Geospatial Analysis! We carefully designed the hands-on exercises to work with real data and offer solutions to real-world problems (from around the globe)! Of course, you'll also learn to create stunning maps :)

    Poništi
  15. 12. ruj 2019.

    really cool meta-RL benchmark environments, wish they were free to use (after the 30-day mujoco trial)!

    Poništi
  16. 3. tra 2019.

    Want to quickly create stunning data visualizations? Come learn with us at Kaggle Learn for only 30 minutes a day: no programming experience required :)

    Poništi
  17. proslijedio/la je Tweet
    20. ožu 2019.

    We introduce PEARL, a new meta-reinforcement learning method that is 20-100x faster and has better end performance than the best prior method. I'm excited to see what this method enables us to do in the real world! w/ K Rakelly, A Zhou, D Quillen

    Poništi
  18. proslijedio/la je Tweet
    6. ožu 2019.

    In collaboration with Google, we're releasing Activation Atlases: a new technique for visualizing what interactions between neurons can represent. 💻Blog: 📝Paper: 🔤Code: 🗺️Demo:

    Poništi
  19. proslijedio/la je Tweet
    4. ožu 2019.

    We’re releasing a Neural MMO — a massively multiagent game environment that supports numerous populations of agents: - Code: - 3D Client:

    Poništi
  20. proslijedio/la je Tweet
    21. velj 2019.

    Today we are excited to release the MuJoCo Soccer environment and accompanying paper, Emergent Coordination through Competition: Environment: Sample gameplay:

    Prikaži ovu nit
    Poništi
  21. proslijedio/la je Tweet
    14. velj 2019.

    We've trained an unsupervised language model that can generate coherent paragraphs and perform rudimentary reading comprehension, machine translation, question answering, and summarization — all without task-specific training:

    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:

    ·