Deep Learning is changing the paradigms of automotive software development. Vehicles will act as a mobile sensor with a huge computing power, and will become more intelligent when connected to the environment. Cumbersome feature extraction algorithm design which requires years of experience are often outperformed by Deep Learning models. We will reach truly cognitive cars at the end of this development, which can handle even the most challenging traffic situations, and interact seamlessly with drivers and surroundings. But that comes with new challenges for the automotive industry. This session gives an overview of AI applications, learning mechanisms, hardware requirements as well as architectures in connection with an IT backend.