Tweets
- Tweets, current page.
- Tweets & replies
- Media
You blocked @quocleix
Are you sure you want to view these Tweets? Viewing Tweets won't unblock @quocleix
-
Quoc Le Retweeted
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)https://twitter.com/lmthang/status/1222234237262159872 …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Quoc Le Retweeted
This video explains
@GoogleAI '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!" https://youtu.be/STrrlLG15OY#100DaysOfMLCodeThanks. Twitter will use this to make your timeline better. UndoUndo -
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.pic.twitter.com/lpOZpsvDck
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
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
@Blonkhartpic.twitter.com/AmTobwf9A0
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
You can find some sample conversations with the bot here:https://github.com/google-research/google-research/blob/master/meena/meena.txt …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
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: https://arxiv.org/abs/2001.09977 Blog: https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html …pic.twitter.com/5SOBa58qx3
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Quoc Le Retweeted
This video explains AdvProp from
@GoogleAI! This technique leverages Adversarial Examples for ImageNet classification by using separate Batch Normalization layers for clean and adversarial mini-batches. https://youtu.be/KTCztkNJm50#100DaysOfMLCodeThanks. Twitter will use this to make your timeline better. UndoUndo -
Quoc Le Retweeted
Some nice case studies about how
@GCPcloud'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.https://cloud.google.com/blog/products/ai-machine-learning/ai-and-machine-learning-improve-manufacturing-visual-inspection-process …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Pretrained checkpoints in Pytorch: https://github.com/rwightman/gen-efficientnet-pytorch … h/t to
@wightmanrShow this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
AdvProp improves accuracy for a wide range of image models, from small to large. But the improvement seems bigger when the model is larger.pic.twitter.com/13scFaoQzB
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
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 threadThanks. Twitter will use this to make your timeline better. UndoUndo -
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 threadThanks. Twitter will use this to make your timeline better. UndoUndo -
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.https://twitter.com/tanmingxing/status/1199046124348116993 …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
EfficientDet: a new family of efficient object detectors. It is based on EfficientNet, and many times more efficient than state of art models. Link: https://arxiv.org/abs/1911.09070 Code: coming soonpic.twitter.com/2KYabAnpLL
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
RandAugment was one of the secret sources behind Noisy Student that I tweeted last week. Code for RandAugment is now opensourced.https://twitter.com/barret_zoph/status/1196621040064974849 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
I also highly recommend this nice video that explains the paper very well:https://www.youtube.com/watch?v=Y8YaU9mv_us …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
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 threadThanks. Twitter will use this to make your timeline better. UndoUndo -
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
pic.twitter.com/BhwgJvSOYK
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
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.