Active Learning for event detection in large-scale information networks.

The project aims at teaching a safety system in a vehicle, connected to the cloud, to detect rare events in the surrounding traffic environment as quickly and as reliably as possible. The challenge lies in the large number of hypotheses, the noisy observations, and the limited prior knowledge on the rare events.Using data sharing, where information is extracted from massive data streams, a collective learning in large complex networks is being built up.

Partner organizations

• Cornell University (Academic, USA)