This paper has a very clear presentation of different attention architectures in transformers. I’d be thankful if people could share their experience in trying multi-query vs standard multi-head attention. Thanks https://t.co/aY1AW5etWI
— Nando de Freitas 🏳️🌈 (@NandoDF) March 13, 2022
Very interesting work on Unsupervised Feature Selection using Supervised Algorithms. It turns out that even for unsupervised learning, XGBoost is all you need. :)
— Bojan Tunguz (@tunguz) March 12, 2022
Blog post: https://t.co/o2nC7wUl7d
Code repo: https://t.co/aOR3mJ9VEy#machinelearning #unsupervisedlearning pic.twitter.com/PZVKxGBgfl
The latest contribution to the Sharpened Cosine Similarity project is a PyTorch Lightning demo from @PSodmann. It shows off the streamlined coding patterns @PyTorchLightnin is famous for.https://t.co/KZUuaOoAF1
— Brandon Rohrer (@_brohrer_) March 12, 2022
ARE YOU FUCKING KIDDING ME
— Jacqueline Nolis 🏳️⚧️ (@skyetetra) March 11, 2022
...so much of my life wasted typing `View(df)` https://t.co/7HbiNERtkD
A nice and telling comparison from Navigator Research pic.twitter.com/LuAcs20xxI
— Nate Cohn (@Nate_Cohn) March 11, 2022
Announcing PyTorch 1.11, TorchData, and functorch!
— PyTorch (@PyTorch) March 10, 2022
Highlights:
- TorchData, a new library for common modular data loading primitives
- functorch adds composable function transforms
- DDP static graph optimizations in stable
Learn more👇https://t.co/WAIjrEguOg
Temporal Difference Learning for Model Predictive Control
— AK (@ak92501) March 10, 2022
abs: https://t.co/WaBa3e5J0s
project page: https://t.co/30YjYkXjwW pic.twitter.com/Yz0Wg4lGDO
On the surprising tradeoff between ImageNet
— AK (@ak92501) March 10, 2022
accuracy and perceptual similarity
abs: https://t.co/FAWkG1OIX5
show that an inverse-U relationship exists between accuracy and PS across a number of settings pic.twitter.com/GHnj2MJUgP
Introducing Ithaca, the first deep neural network for textual restoration, as well as geographical and chronological attribution of ancient Greek inscriptions.
— DeepMind (@DeepMind) March 9, 2022
Out today in @nature, Ithaca aims to assist historians & better understand ancient history: https://t.co/iGcx323enn 1/ pic.twitter.com/R5XnHfDFAi
EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers
— AK (@ak92501) March 9, 2022
abs: https://t.co/Ju4EJMasSZ pic.twitter.com/wZSb4v8ZVv
“Sports Data & Visualization with R: Code, data and visuals for storytellers” - free online book version of @mattwaite's sports analytics #rstats class at University of Nebraska-Lincoln
— Sharon Machlis (@sharon000) March 8, 2022
Matt was key developer of PolitiFact, which won a Pulitzer in 2009.https://t.co/pUgcqp6by4 pic.twitter.com/tDAN4yQwOr
The (Un)Surprising Effectiveness of Pre-Trained Vision Models for Control
— AK (@ak92501) March 8, 2022
abs: https://t.co/kFVZx80f2u pic.twitter.com/Tm723A7aqC
