Tweets

You blocked @quocleix

Are you sure you want to view these Tweets? Viewing Tweets won't unblock @quocleix

  1. Retweeted
    Jan 28

    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)

    Show this thread
    Undo
  2. Retweeted
    Jan 29

    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!"

    Undo
  3. Jan 29

    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.

    Show this thread
    Undo
  4. Jan 29

    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

    Show this thread
    Undo
  5. Jan 28

    You can find some sample conversations with the bot here:

    Show this thread
    Undo
  6. Jan 28

    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:

    Show this thread
    Undo
  7. Retweeted
    3 Dec 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.

    Undo
  8. Retweeted

    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.

    Undo
  9. 25 Nov 2019
    Show this thread
    Undo
  10. 25 Nov 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.

    Show this thread
    Undo
  11. 25 Nov 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.

    Show this thread
    Undo
  12. 25 Nov 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.

    Show this thread
    Undo
  13. 25 Nov 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.

    Show this thread
    Undo
  14. 21 Nov 2019

    And latency on CPU and GPU:

    Show this thread
    Undo
  15. 21 Nov 2019

    Architecture of EfficientDet

    Show this thread
    Undo
  16. 21 Nov 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

    Show this thread
    Undo
  17. 18 Nov 2019

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

    Undo
  18. 12 Nov 2019

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

    Show this thread
    Undo
  19. 12 Nov 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

    Show this thread
    Undo
  20. 12 Nov 2019

    Full comparison against state-of-the-art on ImageNet. Noisy Student is our method. Noisy Student + EfficientNet is 11% better than your favorite ResNet-50 😉

    Show this thread
    Undo

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

    You may also like

    ·