PREMIA (Singapore)

We are pleased to invite you to the following seminar talk jointly organized by Institute for Infocomm Research (I2R) and Pattern Recognition and Machine Intelligence Association (PREMIA):

Kernel-based Learning and Applications

Prof. Klaus-Robert Mueller
Intelligent Data Analysis Group, Fraunhofer FIRST, Berlin, Germany.
Neuroinformatics Chair, Department of Computer Science, University of Potsdam, Germany.

Date: Tuesday, January 11, 2005

Time: 3:00 PM – 4:30 PM

Venue: Lecture Theatre 3, NTU. (NS4-2-32)

Admission: Admission is free

Registration: Please register online via http://www.premia-sg.org/index.php?option=com_events&event_id=6&task=register
(Registration is closed now).

Synopsis:

This lecture provides an introduction to Support Vector Machines, Kernel Principal Component analysis as examples for successful kernel-based learning algorithms. At first, Prof Mueller will give a short background about VC theory and kernel feature spaces and then proceed to kernel based learning in supervised and unsupervised scenarios including some practical and algorithmic considerations. Some of the recent work on kernel-based nonlinear source separation will be discussed. In this talk, Prof Mueller will illustrate the usefulness of kernel algorithms by finally presenting applications such as DNA and biomedical data analysis.

Biography:

Prof. Müller received his PhD degree in Computer Science from Institute for Logics, Complexity and Deduction Systems (University Karlsruhe) in 1992. He is now a full professor for neuroinformatics at University of Potsdam and Department Head of IDA group at Fraunhofer FIRST, Germany. From Dec 1992 to Dec 1993, he was a Research Fellow at the German National Research Center for Computer Science, GMD FIRST, Berlin, working on segmentation and classification with statistical and “neural” methods for time-series analysis. From March 1994 to July 1995, he was a Visiting Researcher at University of Tokyo, with Prof. Dr. S. Amari, working on learning curves and generalization in neural networks. He obtained his tenure position in 1995 as Department Head of the Intelligent Data Analysis (IDA) group at GMD FIRST, Berlin, working on learning theory (Support Vector Machines, Neural Networks, Boosting), analysis of nonstationary time-series, blind separation, and their applications on MEG, EEG, OCR, financial data, acoustics. He is a co-founder of the spin-off company idalab in Berlin. He was a Visiting Researcher at AT&T Bell Labs with Dr. LeCun and Prof. Vapnik, Salk Institute with Prof. Sejnowski, Isaac Newton Institute for Mathematical Sciences, University of Cambridge, Microsoft Research at Redmond, and so on. He served in scientific committees for various international conferences, such as NIPS, ICANN, ICA, COLT, NNSP, ICML, SBRN, etc. He is an Associate Editor for Computational Statistics (Springer) and IEEE Transactions on Biomedical Engineering. He is a reviewer for various international journals, such as Nature, IEEE Transactions on Neural Networks, Signal Processing, PAMI, Biomedical Engineering, Systems, Circuits and Systems, Neural Systems and Rehabilitation Engineering, etc, Signal Processing, Neural Computation, Neural Networks, NeuroComputing, Computational Statistics, Statistics, Machine Learning, and so on. He is a reviewer for various grants, such as Alexander von Humboldt foundation, German Science Foundation, BMBF, Swiss National Science Foundation, Austrian Science Foundation, Netherlands Organization for Scientific Research, Hong-Kong Research Grants Council. He is a consultant to Microsoft, Overture, KPMG, VW, Schering, IBM, etc. He received various awards and honors, such as Fellowship of Landesgraduiertenfoerderung Baden-Württemberg, EU STP Fellowship for Japan, GMD best project award (CANDY & KALIF), and Olympus prize for pattern recognition awarded by the German Pattern Recognition Society (DAGM). He has more than 13 books or book chapters, and more than120 peer-reviewed journal and conference papers.