One of the most prominent scientific challenges of our time is to cope with the complexity which arises in biology, medicine, engineering, economics, sociology and many other areas of high societal relevance. Learning systems are able to perceive large and complex information, and they can adjust and adapt their behavior to influences from their environment. Natural learning systems are, for example, the brain, the nervous system, and living organisms down to the smallest scales and bacteria. Artificial learning systems are, for example, robots that can adapt their behavior to their environments, or software systems with machine learning abilities and making predictions based on big data sets.
Natural as well as artificial learning systems are often influenced by highly unreliable, stochastic factors. Both the natural sciences and the engineering sciences with their complementary scientific methods of analysis and synthesis explore such learning systems by interacting with them, by modeling them, and by explicit construction or reconstruction. However, to date a general understanding of learning systems and a comprehensive approach to their analysis and design is still largely missing. The goals of the Max Planck ETH Center for Learning Systems are to achieve a fundamental understanding of perception, learning and adaption in complex systems, by providing a platform for exchange in research and education.