Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Microsoft Research Blog
Newly discovered principle reveals how adversarial training can perform robust deep learning
In machine learning, adversarial examples usually refer to natural inputs plus small, specially crafted perturbations that can fool the model into making mistakes. In recent years, adversarial examples have been repeatedly discovered in deep learning…
Publication
Policy Improvement from Multiple Experts
Video
Teaching a robot to see and navigate with simulation
The ability to see and navigate is a critical operational requirement for robots and autonomous systems. However, building a real-world autonomous system that can operate safely at scale is a very difficult task. The partnership…
Publication
AvE: Assistance via Empowerment
Tool
WMG_agent
WMG is a transformer-based RL agent that attends to a dynamic set of vectors representing observed and recurrent state.
Tool
TartanAir
TartanAir dataset: AirSim Simulation Dataset for Simultaneous Localization and Mapping theairlab.org/tartanair-dataset (opens in new tab)
Video
TRAC Workshop 2020 – Report Out and Closing Remarks (Day 2)
Trustworthy and Robust AI Collaboration (TRAC) Workshop Eric Horvitz, Microsoft Research and Daniela Rus, Massachusetts Institute of Technology Aleksander Mądry, Massachusetts Institute of Technology and Evelyne Viegas, Microsoft Research
