Collaborative learning — for robots
Algorithm lets independent agents collectively produce a machine-learning model without aggregating data.
Algorithm lets independent agents collectively produce a machine-learning model without aggregating data.
A new algorithm lets networks of Wi-Fi-connected cars, whose layout is constantly changing, share a few expensive links to the Internet.
New algorithms could enable heaps of ‘smart sand’ that can assume any shape, allowing spontaneous formation of new tools or duplication of broken mechanical parts.
Decentralized wireless networks could have applications in distributed sensing and robotics and maybe even personal communications.
A new algorithm enables much faster dissemination of information through self-organizing networks with a few scattered choke points.
An MIT project provides a way to preserve information in constantly changing networks, without resorting to a shared server.