Isaac Kargar

@kargarisaac

Ph.D. student at the Intelligent Robotics Group at Aalto University. Working on , , and .

Finland
linkedin.com/in/eshagh-karg…
Vrijeme pridruživanja: siječanj 2011.
Rođen/a 21. ožujka 1991.
101 fotografija ili videozapis Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @kargarisaac

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

  1. proslijedio/la je Tweet
    prije 16 sati

    Novel Corona Virus 2019 Dataset published by

    7 proslijeđenih tweetova 10 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    2. velj

    Advice for ML research by J. Schulman: Idea is cheap. Choosing the right problems is more important than technical skill. Goal-driven research is basically better than idea-based one. Switching problems too frequently is bad. Read textbooks and theses.

    14 proslijeđenih tweetova 25 korisnika označava da im se sviđa
    Poništi
  3. prije 21 sat

    Distill and transfer learning for robust multitask RL

    2 korisnika označavaju da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    2. velj

    “At Tesla, using AI to solve self-driving isn’t just icing on the cake, it the cake” - Join AI at Tesla! It reports directly to me & we meet/email/text almost every day. My actions, not just words, show how critically I view (benign) AI.

    1.285 replies 4.493 proslijeđena tweeta 39.640 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    2. velj

    So I had a very characteristic phantom brake event today near an overpass. I recorded the data and.... I still don't understand why. The leading theory for those was spurious radar returns. So I visualized all returns +-3m offset of car and there's nothing super high confidence

    53 proslijeđena tweeta 472 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    31. sij

    How do you teach an system to understand humans' preferences if humans aren't always sure what they want? HAI affiliates , Stuart Russell and Yoshua Bengio are exploring the answers.

    35 proslijeđenih tweetova 80 korisnika označava da im se sviđa
    Poništi
  7. 1. velj

    Multi-Agent Imitation and Inverse Reinforcement Learning

    6 korisnika označava da im se sviđa
    Poništi
  8. 1. velj

    Normalizing flows by

    3 korisnika označavaju da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    30. sij

    We're 🎉 Launching a new free course on Deep with UnityML 🥳 you can check the syllabus here 🕹️:

    12 proslijeđenih tweetova 28 korisnika označava da im se sviđa
    Poništi
  10. 31. sij

    Multitask and Transfer Learning: concepts, use-cases, & challenges

    2 proslijeđena tweeta 7 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    29. sij

    Research labs have made incredible advances in combining AI & robotics, but bringing them into the real-world has been a completely different story. I visited that says it has cracked the nut and is ready to take on warehouse floors by storm.

    16 proslijeđenih tweetova 29 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    21. sij

    The world has not yet come to a consensus on whether Elon Musk is building a better future 🌍⚡️🚀, or a secret volcano lair 🌋. Oh, by the way: x drops today 💣 In this video, he’s sharing his story — raw & uncut.

    227 replies 428 proslijeđenih tweetova 2.248 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    30. sij

    We're standardizing OpenAI's deep learning framework on PyTorch to increase our research productivity at scale on GPUs (and have just released a PyTorch version of Spinning Up in Deep RL):

    25 replies 549 proslijeđenih tweetova 1.920 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    30. sij

    Humans learn from curriculum since birth. We can learn complicated math problems because we have accumulated enough prior knowledge. This could be true for training a ML/RL model as well. Let see how curriculum can help an RL agent learn:

    5 replies 162 proslijeđena tweeta 758 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    29. sij

    New blog post: Contrastive Self-Supervised Learning. Contrastive methods learn representations by encoding what makes two things similar or different. I find them very promising and go over some recent works such as DIM, CPC, AMDIM, CMC, MoCo etc.

    8 replies 99 proslijeđenih tweetova 452 korisnika označavaju da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    29. sij

    ML Fairness Gym is a set of components for building simple simulations that explore the potential long-run impacts of deploying machine learning-based decision systems in social environments, based on OpenAI Gym interface.

    1 reply 72 proslijeđena tweeta 272 korisnika označavaju da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    29. sij

    PolyGame: An open-source framework for training AI players through self-play. Deals with many games, board size variation, partial observability... Interesting generalization tidbit: It plays Go on 19x19 at very good level after training only on 13x13.

    5 replies 122 proslijeđena tweeta 349 korisnika označava da im se sviđa
    Poništi
  18. 28. sij

    Rural Roads and Intersections | openpilot CHALLENGE #1 | 0.7.1 self-driving

    Poništi
  19. proslijedio/la je Tweet
    27. sij

    We made the first place at the NuScenes Tracking Challenge (AI Driving Olympics ) Spoiler alert: It's a Kalman filter! We beat the AB3DMOT baseline by a large margin. arXiv

    42 proslijeđena tweeta 210 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. 26. sij

    Hans Rosling: The best stats you've ever seen | TED Talk

    Poništi

@kargarisaac još nije objavio nijedan Tweet.

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:

    ·