Top news of the week: 07.09.2022.
Transformers are Sample Efficient World Models
Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been ...
Indaba
After not taking place these past two years, we excited to announce the Deep Learning Indaba for 2022 that will be held in Tunis, Tunisia, from the 21st to the 26th of …
The Age of Open Foundation Models
Google Brain and Meta AI, research labs established in 2011 and 2012, fruitfully combined longtime academic researchers in deep learning with their key fuels: cloud computing …
Why isn’t there more training on the edge?
One of the most frequent questions I get asked from people exploring machine learning beyond cloud and desktop machines is “What about training?”. If you look around at the popular fram…
Professional news: I've joined Hugging Face 🤗 as product designer.
samim.io - blogging, research, projects, ideas
PaddlePaddle / PaddleHub Public
Awesome pre-trained models toolkit based on PaddlePaddle.(300+ models including Image, Text, Audio and Video with Easy Inference & Serving deployment) - GitHub - PaddlePaddle/PaddleHub: ...
‘Someone had to be first': Pueblo artist criticized after AI painting wins at Colorado State Fair
A game designer from Pueblo West has gone viral for his art made with artificial intelligence after winning a top prize at the Colorado State Fair.
White Paper: State of AI for Earth Observation
Authors: Freddie Kalaitzis, Maral Bayaraa & Cristian Rossi Introduction: This work is a brief survey of AI for Earth Observation, broken down into the following themes: sensor data, machine ...