DeepFly3D: the deep-learning way to design fly-like robots
EPFL scientists have developed a deep-learning based motion-capture software that uses multiple camera views to model the movements of a fly in three dimensions. The ultimate aim is to use this knowledge to design fly-like robots.
Controlling superconducting regions within an exotic metal
Researchers at EPFL have created a metallic microdevice in which they can define and tune patterns of superconductivity. Their discovery, which holds great promise for quantum technologies of the future, has just been published in Science.