Quoc Le

@quocleix

Principal Scientist, Google Brain Team.

Mountain View, CA
scholar.google.com/citations?user…
Vrijeme pridruživanja: travanj 2018.
32 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @quocleix

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

  1. proslijedio/la je Tweet
    prije 22 sata

    About data (asked by & others): 1. Only one occurrence of "Hayvard" in the training data. 2. The sentence that contains "Hayvard" has meaning similar to "Guess what, I obtained my bachelor from Hayvard." 3. No occurrence of "cow*" in the same conversation.

    My favorite conversation is below. The Hayvard pun was funny but I totally missed the steer joke at the end until it was pointed out today by
    Prikaži ovu nit
    20 proslijeđenih tweetova 101 korisnik označava da mu se sviđa
    Poništi
  2. proslijedio/la je Tweet
    28. sij

    Enabling people to converse with chatbots about anything has been a passion of a lifetime for me, and I'm sure of others as well. So I'm very thankful to be able to finally share our results with you all. Hopefully, this will help inform efforts in the area. (1/4)

    Introducing , a 2.6B-param open-domain chatbot with near-human quality. Remarkably, we show strong correlation between perplexity & humanlikeness! Paper: Sample conversations:
    Prikaži ovu nit
    39 proslijeđenih tweetova 173 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    29. sij

    This video explains 's amazing new Meena chatbot! An Evolved Transformer with 2.6B parameters on 341 GB / 40B words of conversation data to achieves remarkable chatbot performance! "Horses go to Hayvard!"

    61 proslijeđeni tweet 277 korisnika označava da im se sviđa
    Poništi
  4. 30. sij

    I had another conversation with Meena just now. It's not as funny and I don't understand the first answer. But the replies to the next two questions are quite funny.

    11 proslijeđenih tweetova 54 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. 29. sij

    My favorite conversation is below. The Hayvard pun was funny but I totally missed the steer joke at the end until it was pointed out today by

    5 replies 23 proslijeđena tweeta 155 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. 28. sij

    You can find some sample conversations with the bot here:

    18 proslijeđenih tweetova 116 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. 28. sij

    New paper: Towards a Human-like Open-Domain Chatbot. Key takeaways: 1. "Perplexity is all a chatbot needs" ;) 2. We're getting closer to a high-quality chatbot that can chat about anything Paper: Blog:

    i
    28 replies 629 proslijeđenih tweetova 1.787 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    3. pro 2019.

    This video explains AdvProp from ! This technique leverages Adversarial Examples for ImageNet classification by using separate Batch Normalization layers for clean and adversarial mini-batches.

    29 proslijeđenih tweetova 86 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    26. stu 2019.

    Some nice case studies about how 's AutoML products can help tackle real-world problems in visual inspection across a number of different manufacturing domains, being used by companies like Global Foundries and Siemens.

    1 reply 37 proslijeđenih tweetova 120 korisnika označava da im se sviđa
    Poništi
  10. 25. stu 2019.

    Pretrained checkpoints in Pytorch: h/t to

    9 proslijeđenih tweetova 42 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. 25. stu 2019.

    AdvProp improves accuracy for a wide range of image models, from small to large. But the improvement seems bigger when the model is larger.

    3 proslijeđena tweeta 39 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. 25. stu 2019.

    As a data augmentation method, adversarial examples are more general than other image processing techniques. So I expect AdvProp to be useful everywhere (language, structured data etc.), not just image recognition.

    14 proslijeđenih tweetova 94 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. 25. stu 2019.

    Many of us tried to use adversarial examples as data augmentation and observed a drop in accuracy. And it seems that simply using two BatchNorms overcomes this mysterious drop in accuracy.

    1 reply 9 proslijeđenih tweetova 62 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. 25. stu 2019.

    AdvProp: One weird trick to use adversarial examples to reduce overfitting. Key idea is to use two BatchNorms, one for normal examples and another one for adversarial examples. Significant gains on ImageNet and other test sets.

    Can adversarial examples improve image recognition? Check out our recent work: AdvProp, achieving ImageNet top-1 accuracy 85.5% (no extra data) with adversarial examples! Arxiv: Checkpoints:
    158 proslijeđenih tweetova 567 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. 21. stu 2019.

    And latency on CPU and GPU:

    2 proslijeđena tweeta 26 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. 21. stu 2019.

    Architecture of EfficientDet

    i
    6 proslijeđenih tweetova 78 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. 21. stu 2019.

    EfficientDet: a new family of efficient object detectors. It is based on EfficientNet, and many times more efficient than state of art models. Link: Code: coming soon

    i
    10 replies 232 proslijeđena tweeta 821 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. 18. stu 2019.

    RandAugment was one of the secret sources behind Noisy Student that I tweeted last week. Code for RandAugment is now opensourced.

    *New paper* RandAugment: a new data augmentation. Better & simpler than AutoAugment. Main idea is to select transformations at random, and tune their magnitude. It achieves 85.0% top-1 on ImageNet. Paper: Code:
    85 proslijeđenih tweetova 462 korisnika označavaju da im se sviđa
    Poništi
  19. 12. stu 2019.

    I also highly recommend this nice video that explains the paper very well:

    32 proslijeđena tweeta 158 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. 12. stu 2019.

    Method is also super simple: 1) Train a classifier on ImageNet 2) Infer labels on a much larger unlabeled dataset 3) Train a larger classifier on the combined set 4) Iterate the process, adding noise

    12 replies 38 proslijeđenih tweetova 215 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi

@quocleix 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:

    ·