Kolloquiumsvortrag: Prof. Dr. Thomas Martinetz, Universität zu Lübeck
Kiel, Kaiserstraße 2, Gebäude D, Aquarium
Titel: "Sparse Coding and Deep Networks: the neural paradigms of state-of-the art pattern recognition"
Up to recently humans were by far superior in recognizing and classifying objects. It seemed to be a hard problem to capture the variances and invariances humans can deal with easily in the real world. After many years of research this is slowly changing. Besides highly increased training data sets (big data), two new insights into the information processing principles of the brain now make a difference: i) sparse coding of information, with the "dual" concept of compressed sensing, and ii) deep convolutional networks, which use many layers of artificial simple and complex cells. This talk gives an introduction to these concepts, their historical development, and an overview about their applications in real world problems.