Adversarial robustness as a prior for better transfer learning
Editor’s note: This post and its research are the collaborative efforts of our team, which includes Andrew Ilyas (opens in new tab) (PhD Student, MIT), Logan Engstrom (opens in new tab) (PhD Student, MIT), Aleksander…
The 2nd Workshop on Hot Topics in Video Analytics and Intelligent Edges
Cameras are everywhere! Analyzing live videos from these cameras has great potential to impact science and society. Enterprise cameras are deployed for a wide variety of commercial and security reasons. Consumer devices themselves have cameras with users…
From Paper to Product
I used to think that creating a product from a research paper was a linear process. First, researchers develop the research, and then, engineers figure out how to transform that research idea into product. After…
ZeRO & Fastest BERT: Increasing the scale and speed of deep learning training in DeepSpeed
The latest trend in AI is that larger natural language models provide better accuracy; however, larger models are difficult to train because of cost, time, and ease of code integration. With the goal of advancing…
ZeRO & Fastest BERT: Increasing the scale and speed of deep learning training in DeepSpeed webinar
The latest trend in AI is that larger natural language models provide better accuracy; however, larger models are difficult to train because of cost, time, and ease of code integration. With the goal of advancing…
MineRL Competition 2020
Starting July 1st 2020, we are holding a competition on sample-efficient reinforcement learning using human priors as a part of NeurIPS 2020 competition track. In our competition, participants develop a system to obtain a diamond…