Dein Suchergebnis zum Thema: Trainer

Colour patch could throw self-driving vehicles off track

https://www.mpg.de/14311323/colour-patch-could-throw-self-driving-vehicles-off-track

A team of researchers in Tübingen show that optical flow systems based on deep neural networks – a likely component of future autonomous cars – are vulnerable to adversarial attacks. The computer vision experts are shaking up the automotive industry by warning car manufacturers around the globe that it could take a simple colour pattern to put the brakes on computer vision systems in autonomous cars.
self-driving technology that there is a new possible threat and enable them to train

Attack on autopilots

https://www.mpg.de/14931044/attack-on-autopilots?c=12641819

How fast the development from assisted to fully automated vehicles will progress is uncertain. One crucial factor here is the reliability with which a vehicle can navigate in its surroundings and react to unforeseeable incidents. Our group at the Max Planck Institute for Intelligent Systems showed that methods for motion analysis based on deep neural networks – likely components in future autonomous vehicles – can be confused by small patterns designed to “attack” these networks.
Our work can help manufacturers to train their systems to withstand such disturbances

The Covews algorithm supports Covid-19 mortality forecasts

https://www.mpg.de/16444031/artificial-intelligence-supports-medical-prognoses?c=11969127

The Covews algorithm, developed by a team of researchers at the Max Planck Institute for Intelligent Systems, uses machine learning methods to calculate mortality forecasts for people with Covid 19, for example. The artificial intelligence could thus help to better treat people infected with Corona.
To develop and especially to train Covews, the researchers used 33,000 anonymized