Tweetovi

Blokirali ste korisnika/cu @lukasLansky

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

  1. proslijedio/la je Tweet
    31. sij

    Join Microsoft, live and work in beautiful Prague, and be a leading F# open source community tooling contributor, helping others across the world to contribute to the compiler, library and tools, and help Microsoft deliver these at high quality to users

    Poništi
  2. proslijedio/la je Tweet

    The cental rule in life is that it is much, much better to panic early than late.

    Poništi
  3. proslijedio/la je Tweet
    25. sij

    There's a new book making the rounds, "More From Less", by tech guru . McAfee argues we can have indefinite GDP growth while *reducing* our ecological impact. For evidence, he points to the US economy, which he says has dematerialized since 1980. Big claim. Is it true?

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    22. sij

    FixMatch: focusing on simplicity for semi-supervised learning and improving state of the art (CIFAR 94.9% with 250 labels, 88.6% with 40). Collaboration with Kihyuk Sohn, Nicholas Carlini

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

    this is absolutely nuts. The AI GPT-2 has learned to play chess moderately well (able to give bad human amateurs a game) – despite only being a text AI, learning from a corpus of chess notation text, and not having any concept of what a chessboard is

    Prikaži ovu nit
    Poništi
  6. 6. pro 2019.
    Poništi
  7. proslijedio/la je Tweet
    4. pro 2019.

    Our new paper, Deep Learning for Symbolic Mathematics, is now on arXiv We added *a lot* of new results compared to the original submission. With (1/7)

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    25. stu 2019.

    I hope that MuZero, the latest work by , sets a trend for model learning in RL. It’s a powerful and largely unexplored middle ground between model-based and model-free RL.

    Poništi
  9. proslijedio/la je Tweet
    3. stu 2019.

    When people ask me what is the future of painting or brushes, I tell This is. This shows the power of and working together to enhance human creativity. I extracted and processed the video using the SPADE algorithm and augmented it on the feed.

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    28. lis 2019.

    Emtremely excited to finally share a side-project I've been working on for the past few months: Neural Synesthesia, visualizing music with ! So many ideas left to explore, this journey is just getting started.. More HD renders on my new YT channel:

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    26. ruj 2019.

    Really enjoyed the (non OpenAI) ICLR submission that trained a transformer on symbolic math. The surprise: it beat Mathematica on symbolic integration and diff eq solving by a _very_ big margin!

    Poništi
  12. proslijedio/la je Tweet
    7. srp 2019.

    BigBiGAN shows that "progress in image generation quality translates to substantially improved representation learning performance." Competitive w/self-supervised approaches on ImageNet. The cycle from generative models to other methods and back again continues.

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

    When a Stack Overflow question looks like an E.E. Cummings poem.

    Poništi
  14. proslijedio/la je Tweet
    8. lip 2019.

    "programs are proofs, but most of them are proofs that int implies int" --

    Poništi
  15. proslijedio/la je Tweet
    25. svi 2019.

    This chart has blown my mind.

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet

    Having kids inhibits scientific curiosity. I recently met a toddler who was just learning to talk, and I wondered what would happen if you raised a child only being able to talk to GPT-2, and the parent said no.

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

    playing a game of GANstruction: scales and arpeggios

    Poništi
  18. proslijedio/la je Tweet
    3. svi 2019.

    2. Neural net training fails silently The Essential Reader Illustrated

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    2. svi 2019.

    Architectural machine translation Thanks to for inspiration!

    Poništi
  20. proslijedio/la je Tweet

    shows that follows shipping lanes: As it turns out particles in ship exhaust increase the likelihood and intensity of thunderstorms. Really cool fact that I had never considered! Source:

    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:

    ·