Mikhail Sirotenko

@sirotenko_m

Google(Team Lead)|Dresr(Chief Scientist)| Amazon(Research Scientist)| Samsung(Team Lead). Author of the first public implementation of ConvNets on GPU

Vrijeme pridruživanja: listopad 2010.

Tweetovi

Blokirali ste korisnika/cu @sirotenko_m

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

  1. proslijedio/la je Tweet
    27. stu 2019.

    Gradient descent is used in many ways at Tesla

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet

    MMG | Прокопьевск

    Poništi
  3. 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.

    Poništi
  4. proslijedio/la je Tweet
    28. sij
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    24. sij

    Impressive results on single image depth estimation by Ranftl et al

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

    Spotify’s ‘Paved Road’ approach is music to our ears! 🎧🎶 Discover how utilizes TensorFlow Extended (TFX)'s components such as Data Validation to increase machine learning engineering productivity. Learn more here →

    (from left to right:) Google cloud logo, Kubeflow logo, TensorFlow logo
    Poništi
  7. proslijedio/la je Tweet
    20. sij

    And you *should* be blogging! said: "The top advice I would give my younger self would be to start blogging sooner."

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    20. sij

    Flax: A neural network library for JAX designed for flexibility (pre-release)

    Poništi
  9. proslijedio/la je Tweet

    Amazing frame interpolation by DAIN: Depth Aware Video Frame Interpolation.

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    12. sij

    The funny thing about AIDungeon is due to all the GPT-2 pre-training on swaths of random web text, you can create an adventure game about literally anything. Here's one about installing OpenCV from source:

    Poništi
  11. proslijedio/la je Tweet
    16. sij

    I think I'd never really watched a pole vault in such slow motion from this angle. It truly is an incredibly complex motion!

    Poništi
  12. proslijedio/la je Tweet
    13. sij

    These new images from the Hubble telescope are weird and wonderful enough that they need a little decoding (a short thread).

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

    Mathematical Reasoning in Latent Space will be featured at . Multiple step reasoning can be performed on embedding vectors of mathematical formulas.

    Poništi
  14. proslijedio/la je Tweet
    11. sij

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

    Poništi
  15. proslijedio/la je Tweet

    Loving this trend of impressive new scientific sites. What else is in this vein? - : learn quantum computing - : learn ML - : interactive AI journal - : Medium for scientific publishing

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    11. sij

    On the Relationship between Self-Attention and Convolutional Layers This work shows that attention layers can perform convolution and that they often learn to do so in practice. They also prove that a self-attention layer is as expressive as a conv layer.

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    10. sij

    I just wrote a 3-part blog post on optimizing sample sizes in A/B testing. It's kind of a longread, so if you just want the elevator pitch, here's a tweetstorm (1/20):

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    9. sij

    What I did over my winter break! It gives me great pleasure to share this summary of some of our work in 2019, on behalf of all my colleagues at & .

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    9. sij

    Watched "The Squire — AI Written Short Film". It's a live-action adaption of AI Dungeon gameplay. Super fun to see!

    Poništi
  20. proslijedio/la je Tweet
    3. sij

    A General and Adaptive Robust Loss Function They propose an analytical function that can represent a family of well known robust cost functions just with a single parameter (alpha). Alpha lets you walk through L2, huber, cauchy, tukey and more.

    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:

    ·