Learning machines that perceive, act and communicate

Humans are very good in perceiving all kinds of high-dimensional sensory inputs, extracting the meaningful information and acting on that information to pursue their goals. Having this in mind, our vision is a learning system, that takes raw, potentially high-dimensional sensory inputs (e.g. raw image data), extracts the relevant information, and learns to act by experiencing success or failure. In this talk I will provide some first successful examples along this line of research. In particular, I will discuss neural network based architectures and algorithms that are the basic building blocks of our neural control architecture.