In this seminar, recent papers of the pattern recognition and machine learning literature are presented and discussed. Possible topics cover statistical models in computer vision, graphical models and machine learning.

The course covers advanced methods of statistical learning :PAC learning and statistical learning theory;variational methods and optimization, e.g., maximum entropy techniques, information bottleneck, deterministic and simulated annealing; clustering for vectorial, histogram and relational data; model selection; graphical models

The course introduces fundamental concepts and algorithms of machine Learning:Bayes decision theory and maximum likelihood estimation,cross-validation, jackknife and bootstrap, hypothesis testing,classification techniques: perceptron, support vector machines,density estimation, unsupervised learning, hidden markov models,dimensionality reduction techniques.

Problem oriented course in scientific computing with emphasis onoptimization and modeling.linear and nonlinear least squares,sensitivity analysis,constraint minimization (Lagrange multipliers),conjugate gradient method,SVD,Linear programming,support vector classification,variational calculus,linear filter theory,nonlinear diffusion,dynamic programming,parsimony

Problem oriented course in scientific computing with emphasis onoptimization and modelling:Linear and nonlinear least squares, sensitivity analysis, constraint minimization (Lagrange multipliers) , conjugate gradient methodSVD, Linear programming, support vector classification, variational calculus, linear filter theory (Wiener filter), nonlinear diffusion, dynamic programming, parsimony.

The course covers advanced methods of statistical learning:- Variational methods and optimization.- Deterministic annealing.- Clustering for diverse types of data.- Model validation by information theory.

This course acquaints students with core knowledge in computer graphics, image processing, multimedia and computer vision. Topics include: Graphics pipeline, perception and camera models, transformation, shading, global illumination, texturing, sampling, filtering, image representations, image and video compression, edge detection and optical flow.

This course acquaints students with core knowledge in computer graphics, vision and learning. Topics include: Graphics pipeline, perception and camera models, transformation, shading, global illumination, texturing, sampling, filtering, edge detection, Bayes decision theory, classification, support vector machines, dimensionality reduction, clustering, Bayes nets.