So it turns out that Language Modelling with Approximate Outputs (LMAO) idea I've been working on for spaCy works well! So well that the work must have been finished before I even started 🤷♂️Great paper by Kumar and Tsevtkov 👉 https://t.co/TLJ9a42c0K
— Matthew Honnibal (@honnibal) December 14, 2018
A Style-Based Generator Architecture for Generative Adversarial Networks. @NvidiaAI does it again! https://t.co/W2Av34ta9O pic.twitter.com/wkDJgt8v3q
— hardmaru (@hardmaru) December 13, 2018
These style-based generator results look great: https://t.co/RL825n0yNP pic.twitter.com/k7UtJMTWhM
— Ian Goodfellow (@goodfellow_ian) December 13, 2018
Introducing Grasp2Vec, a method of acquiring effective object-centric representations for robotic manipulation tasks, without human labeling, by using autonomous robot interactions with the environment. Learn more at ↓ https://t.co/Q7j6nNXI1C
— Google AI (@GoogleAI) December 11, 2018
Zooming in allows one to get a glimpse of the world before our time. pic.twitter.com/9Z3rMbwyLD
— hardmaru (@hardmaru) December 11, 2018
Learning More with Less by @DataLives https://t.co/hYMQN3DDZ4
— Jeremy Howard (@jeremyphoward) December 10, 2018
Great to see folks doing additional ablation experiments beyond those we already did in the ULMFiT paper. This work shows that even just a little unlabeled data helps a lot!
This is a far better-than-average paper. Sensible, yet simple approach, with very usable code provided, and well-designed experiments. Transfer learning accuracy on Pascal increases from 70%->75% - not bad! https://t.co/RGaRtADrlh
— Jeremy Howard (@jeremyphoward) December 10, 2018
The "Cross-View Training" paper by Clark et al came out two weeks before BERT, and I think it's got lost in the noise. It's worth paying attention to: their self-training trick is very elegant, and seems easy to apply and extend. https://t.co/0kjTCuun00
— Matthew Honnibal (@honnibal) December 10, 2018
"Applied Federated Learning: Improving Google Keyboard Query Suggestions," Yang, Andrew, and Eichner et al.: https://t.co/Rc474K1irC
— Miles Brundage (@Miles_Brundage) December 10, 2018
"Adversarial Transfer Learning," Wilson and Cook: https://t.co/gf5aKGgwBw
— Miles Brundage (@Miles_Brundage) December 10, 2018
Looks like a good review
Key Papers in Deep RL
— ML Review (@ml_review) December 10, 2018
by @OpenAI
List of papers in deep RL that should provide a useful starting point for someone looking to do research in the field.https://t.co/juwFAdKtLs pic.twitter.com/lo0wgLcoeT
SpaceSheets: Interactive Latent Space Exploration through a Spreadsheet Interface
— hardmaru (@hardmaru) December 9, 2018
Who would have thought that spreadsheets can be used as a highly effective interface for creative latent space exploration? Very impressive work & demo to end #NeurIPS2018https://t.co/EmwXu0GWb5 https://t.co/LoPvwWrr5J
