ConVIRT—Contrastive Learning of Visual Representations from Paired Images & Text—by @yuhaozhangx @hjian42 Miura @chrmanning @curtlanglotz pioneers effective use of human-written descriptive text to improve unsupervised contrastive learning from images https://t.co/HuKfDUTrxv pic.twitter.com/Z62R9FJ1rk
— Stanford NLP Group (@stanfordnlp) March 1, 2021
Very impressive Denoising Transformer Auto-Encoder 1st place solution for the February 2021 @Kaggle Competition. Congratulations to @ryanzjlib on such a brilliant work!https://t.co/7cOsWRV4mE#ML #DL #datascience pic.twitter.com/DOAYoJpREG
— Bojan Tunguz (@tunguz) March 1, 2021
Named Tensor Notation (v1.0 release w/ @davidweichiang, @boazbaraktcs ) - a "dangerous and irresponsible" proposal for reproducible math in deep learning.
— Sasha Rush (@srush_nlp) March 1, 2021
PDF: https://t.co/1jvhpG7yCH
Comments: https://t.co/76h9E1bUWT
Why not Einsum? https://t.co/St0anL4v74 pic.twitter.com/gbdGUBSS0C
New tutorial!🚀
— Adrian Rosebrock (@PyImageSearch) March 1, 2021
Adversarial attacks with FGSM (Fast Gradient Sign Method)
- Implement FGSM with #Keras and #TensorFlow
- Fool CNNs
- Full tutorial w/ #Python codehttps://t.co/yAHUG9GBFf 👍#DeepLearning #MachineLearning #ArtificialIngelligence #AI #DataScience #OpenCV pic.twitter.com/Xb5O8ccbv8
Just because something involves technology doesn't mean it's progress. Progress involves creating value in people's lives.
— François Chollet (@fchollet) March 1, 2021
ai: automatically aggregating the knowledge of the internet https://t.co/6PD0AQvQCp
— Janelle Shane (@JanelleCShane) February 28, 2021
Nice video by Abhishek about his AutoNLP project! Check it out https://t.co/dzavvR74vl
— Thomas Wolf (@Thom_Wolf) February 28, 2021
Just stumbled upon this nice repo listing challenges and contests suitable for applying machine learning/deep learning. 33 challenges CVPR 2021-related challenges were just added. Something interesting to consider for student projects/homeworks https://t.co/KPviKe22Db
— Sebastian Raschka (@rasbt) February 27, 2021
This is fun: Draw an iceberg and see how it floats.
— Randy Olson (@randal_olson) February 26, 2021
Try your own here: https://t.co/KxEHukaxkH pic.twitter.com/WPVzzmftPy
Thinking about doing a periodic thread of lesser-known seaborn features or tricks.
— Michael Waskom (@michaelwaskom) February 26, 2021
First up: most functions will do something sensible for many types of input, like this dict of Series with different lengths.
(Surprised? You may want to read this: https://t.co/VF2ugu9ICO) pic.twitter.com/gMjl3WKmzo
What percentage of all fossil fuel emissions have occurred in your lifetime? Use this #dataviz to find out.
— Randy Olson (@randal_olson) February 26, 2021
Source: https://t.co/rBW5pAqfXp pic.twitter.com/tjIPNg3E3L
Thanks again @PyDataMTL for inviting me to speak tonight. Here are my slides from the talk on how to finetune (large) Transformers models.https://t.co/H2P2PvlfS4
— Sylvain Gugger (@GuggerSylvain) February 26, 2021
