Vivek Singhal

@vsinghalus

Co-Founder, CellStrat & AI Data Scientist

Bengaluru, India
Vrijeme pridruživanja: rujan 2010.

Tweetovi

Blokirali ste korisnika/cu @vsinghalus

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

  1. prije 26 minuta
    Poništi
  2. prije 26 minuta
    Poništi
  3. prije 27 minuta
    Poništi
  4. prije 27 minuta
    Poništi
  5. prije 4 sata

    Excited to attend CellStrat AI Conclave - Retail & Ecom (AI Industry Conference in Bangalore)! Who else is interested?

    Poništi
  6. proslijedio/la je Tweet
    prije 20 sati

    Our latest paper, ☢️ Radioactive data: tracing through training, is now on arXiv. TL;DR: you can modify your data in an imperceptible way so that any model trained on it will have an identifiable mark. (1/7)

    Prikaži ovu nit
    Poništi
  7. prije 7 sati
    Poništi
  8. prije 21 sat
    Poništi
  9. 3. velj
    Poništi
  10. 3. velj

    .0 Attend Bengaluru's leading AI conference - the "CellStrat AI Conclave" on 8th Feb, Saturday on topic of "AI Disruptions for Retail and Ecommerce". Meet top Retail / Ecommerce AI executives. See demos of…

    Poništi
  11. 3. velj
    Poništi
  12. 3. velj
    Poništi
  13. 3. velj
    Poništi
  14. 3. velj
    Poništi
  15. 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:

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    2. velj
    Poništi
  17. proslijedio/la je Tweet
    3. velj

    Added ImageNet validation results for 164 pretrained models on several datasets, incl ImageNet-A, ImageNetV2, and Imagenet-Sketch. No surprise, models with exposure to more data do quite well. Without extra, EfficientNets are holding their own.

    Prikaži ovu nit
    Poništi
  18. 3. velj
    Poništi
  19. 3. velj
    Poništi
  20. 3. velj
    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:

    ·