Analysis and modeling of brain signals dynamics: some insights and many queries

Fernando Lopes da Silva, M.D., Ph.D.

Emeritus Professor, Center of Neuroscience, Swammerdam Institute for Life Sciences, Science Park 904, Kamer C 3. 274. 1098XH Amsterdam, The Netherlands
Prof. Lopes da Silva is one of the world references in neurosciences. Besides his medical formation he has a strong component on engineering and mathematics. In that sense he is perfect for bridging medicine and engineering.
He was one of the pioneers on neuronal modeling, first at UK and then in Netherlands. He will talk about neurosciences and modeling which is a hot issue and a very appealing topic for engineers and in particular, for the community of pattern recognition.

Computer Recognition of Human Activities, Objects and their Interactions

Professor J.K. Aggarwal

J. K. Aggarwal is on the faculty of The University of Texas at Austin College of Engineering and is currently a Cullen Professor of Electrical and Computer Engineering and Director of the Computer and Vision Research Center. His research interests include computer vision, pattern recognition and image processing focusing on human motion.
A Fellow of IEEE (1976), IAPR (1998) and AAAS (2005), he received the Senior Research Award of the American Society of Engineering Education in 1992, the 1996 Technical Achievement Award of the IEEE Computer Society and the graduate teaching award at The University of Texas at Austin in 1992. More recently, he is the recipient of the 2004 K S FU prize of the International Association for Pattern Recognition, the 2005 Kirchmayer Graduate Teaching Award of the IEEE and the 2007 Okawa Prize of the Okawa Foundation of Japan.. He is a Life Fellow of IEEE and Golden Core member of IEEE Computer Society. He has authored and edited a number of books, chapters, proceedings of conferences, and papers.
Abstract
Computer Vision has graduated from a research tool in the early 1960s to a mature discipline today. The developments in cameras, computers and memory have contributed in part to this maturing of computer vision. Namely, there is an explosive growth in the number of cameras in public places, the speed of computers has increased significantly and the price of memory has spectacularly decreased. The word camera may be used in a very broad sense since the imaging modalities range from the usual cameras imaging a visual intensity image to thermal image and laser range image. The introduction of KINECT by Microsoft has added new dimension to sensing by capturing both RGB and depth information for indoor scenes in a cost effective manner. Further, a large number of applications of computer vision technology are contributing to the solution of a diverse set of societal problems including surveillance and monitoring, driver assistance and autism. Thus, the field of computer vision, research and applications, is experiencing its golden period.
At The University of Texas at Austin, Professor Aggarwal and his group are pursuing a number of projects on human activity understanding and face/emotion recognition. Professor Aggarwal will present his research on modeling and recognition of actions and interactions, including human and object interactions. The object may be a piece of luggage, a car or an unmovable object like a fence. The applications considered include monitoring of human activities in public places, identification of abandoned baggage and face and emotion recognition. The application of KINECT to analyzing activities will be discussed. The issues considered in these problems will illustrate the richness of ideas involved and the difficulties associated with understanding human activities. Application of the above research to surveillance and autism will be discussed together with actual examples and their solutions.

Big Data: where is the information?

Professor Joachim M. Buhmann

Joachim M. Buhmann leads the Machine Learning Laboratory in the Department of Computer Science at ETH Zurich. He has been a full professor of Information Science and Engineering (Informatik) since October 2003. Born in 1959 in Friedrichshafen, Germany, he studied Physics at the Technical University Munich and obtained his PhD in Theoretical Biophysics under the supervision of Professor Klaus Schulten. His doctoral thesis was about pattern recognition in neural networks. He then spent three years as a research associate and assistant professor at the University of Southern California, Los Angeles. In 1991 he worked at the Lawrence Livermore National Laboratory in California. He held a professorship for practical Computer Science (praktische Informatik) at the University of Bonn, Germany from 1992 to 2003. His research interests spans the areas of pattern recognition and data analysis, including machine learning, statistical learning theory and applied statistics. Application areas of his research include image analysis, medical imaging, acoustic processing and bioinformatics. He serves as president of the German Pattern Recognition Society (Deutschen Arbeitsgemeinschaft für Mustererkennung) since 2009, including serving on the board during 2000-2003. He was associate editor for IEEE Transactions on Neural Networks, IEEE Transactions on Image Processing and IEEE Transaction on Pattern Analysis and Machine Intelligence.
Abstract
The digital revolution has created unprecedented opportunities in computing and communication but it also has generated the data deluge with an urgent demand for new pattern recognition technology. Learning patterns in data requires to extract interesting, statistically significant regularities in (large) data sets, e.g. the identification of connection patterns in the brain (connectomics) or the detection of cancer cells in tissue microarrays and estimating their staining as a cancer severity score. Admissible solutions or hypotheses specify the context of pattern analysis problems which have to cope with model mismatch and noise in data. An information theoretic approach is developed which estimates the precision of inferred solution sets and regularizes solutions in a noise adapted way. The tradeoff between "informativeness" and "robustness" is mirrored by the balance between high information content and identifiability of solution sets, thereby giving rise to a new notion of context sensitive information. Cost function to rank solutions and, more abstractly, algorithms are considered as noisy channels with an approximation capacity. The effectiveness of this concept is demonstrated by model validation for spectral clustering based on different variants of graph cuts. The concept also enables us to measure how many bit are extracted by sorting algorithms when the input and thereby the pairwise comparisons are subject to fluctuations.