New on the @FastForwardLabs blog: @shioulin_sam and @NishaMuktewar dive into meta-learning and learning with limited labelled data: https://t.co/lOHx1r5k9S
— Hilary Mason (@hmason) May 22, 2019
New on the @FastForwardLabs blog: @shioulin_sam and @NishaMuktewar dive into meta-learning and learning with limited labelled data: https://t.co/lOHx1r5k9S
— Hilary Mason (@hmason) May 22, 2019
super interesting article on synthetic data and how it's being applied across industries: https://t.co/ewZ3dOscv5
— Josh Tobin (@josh_tobin_) May 22, 2019
CleverHans blog post with @nickfrosst: we explain how the Deep k-Nearest Neighbors (DkNN) and soft nearest-neighbor loss (SNNL) help recognize data that is not from the training distribution. The post includes an interactive figure (credit goes to Nick): https://t.co/aajpf8NOib pic.twitter.com/MKKc4WX8Rp
— Nicolas Papernot (@NicolasPapernot) May 21, 2019
Naver uses TensorFlow to match millions of products daily to over 5,000 shopping categories.
— TensorFlow (@TensorFlow) May 20, 2019
Find out how they improve accuracy and create a more user-friendly shopping experience in this guest article by the engineering team.
Read more here ↓ https://t.co/xbHsGKyhbT
This recent blog post by Graves and Clancy at DeepMind gives a great summary/case for it: https://t.co/45k5ZGiKxy
— Miles Brundage (@Miles_Brundage) May 11, 2019
Lilian Weng of OpenAI deep dives into two prominent pre-trained language models - ULMFiT and OpenAI GPT - and describe how they work in detail. https://t.co/PAm3yLPkyO #AI #ML
— Mariya Yao (@thinkmariya) May 2, 2019
Stochastic Weight Averaging: a simple procedure that improves generalization over SGD at no additional cost.
— PyTorch (@PyTorch) April 29, 2019
Can be used as a drop-in replacement for any other optimizer in PyTorch.
Read more: https://t.co/IRhz40AZKU
guest blogpost by @Pavel_Izmailov and @andrewgwils pic.twitter.com/yU0HKDYr7v
ICYMI, 🙌 Really nice side-by-side for dplyr & #rdatatable syntax…
— Mara Averick (@dataandme) April 26, 2019
"A data.table and dplyr tour" by atrebas https://t.co/dT3cCBKD4G #rstats pic.twitter.com/vr8hxlLMHx
📝 Great write-up on types and uses of documentation.
— Mara Averick (@dataandme) April 16, 2019
❓ "What Docs When" by @gvwilsonhttps://t.co/Ju1jdT6TGU
/* 🖍 scribbles mine */ pic.twitter.com/sXNYC3e2y3
This post by the Snorkel team gives a great overview of ingredients that make up a state-of-the-art approach on GLUE:
— Sebastian Ruder (@seb_ruder) April 11, 2019
1) Traditional supervision
2) Transfer learning
3) Multi-task learning
4) Dataset slicing (motivated by error analysis)
5) Ensemblinghttps://t.co/AcVTfjdiPF pic.twitter.com/3i6gu6X88w
A nice blog post that explains the connections between Attention in Transformers to Dynamic Routing in Capsule Networks https://t.co/ery1X6HVni pic.twitter.com/2OH0xmkMcJ
— hardmaru (@hardmaru) April 9, 2019
This is a great post that highlights the connection between the building blocks used in Transformers and Capsule Networks. Definitely worth reading! https://t.co/VsdzvxY4hN
— Sebastian Ruder (@seb_ruder) April 9, 2019