Search result: Catalogue data in Spring Semester 2015

Computer Science Master Information
Focus Courses
Focus Courses in Visual Computing
Focus Elective Courses Visual Computing
NumberTitleTypeECTSHoursLecturers
252-0526-00LStatistical Learning Theory Information W4 credits2V + 1UJ. M. Buhmann
AbstractThe 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.
ObjectiveThe course surveys recent methods of statistical learning. The fundamentals of machine learning as presented in the course "Introduction to Machine Learning" are expanded and in particular, the theory of statistical learning is discussed.
Content# Boosting: A state-of-the-art classification approach that is sometimes used as an alternative to SVMs in non-linear classification.
# Theory of estimators: How can we measure the quality of a statistical estimator? We already discussed bias and variance of estimators very briefly, but the interesting part is yet to come.
# Statistical learning theory: How can we measure the quality of a classifier? Can we give any guarantees for the prediction error?
# Variational methods and optimization: We consider optimization approaches for problems where the optimizer is a probability distribution. Concepts we will discuss in this context include:

* Maximum Entropy
* Information Bottleneck
* Deterministic Annealing

# Clustering: The problem of sorting data into groups without using training samples. This requires a definition of ``similarity'' between data points and adequate optimization procedures.
# Model selection: We have already discussed how to fit a model to a data set in ML I, which usually involved adjusting model parameters for a given type of model. Model selection refers to the question of how complex the chosen model should be. As we already know, simple and complex models both have advantages and drawbacks alike.
# Reinforcement learning: The problem of learning through interaction with an environment which changes. To achieve optimal behavior, we have to base decisions not only on the current state of the environment, but also on how we expect it to develop in the future.
Lecture notesno script; transparencies of the lectures will be made available.
LiteratureDuda, Hart, Stork: Pattern Classification, Wiley Interscience, 2000.

Hastie, Tibshirani, Friedman: The Elements of Statistical Learning, Springer, 2001.

L. Devroye, L. Gyorfi, and G. Lugosi: A probabilistic theory of pattern recognition. Springer, New York, 1996
Prerequisites / NoticeRequirements:

basic knowledge of statistics, interest in statistical methods.

It is recommended that Introduction to Machine Learning (ML I) is taken first; but with a little extra effort Statistical Learning Theory can be followed without the introductory course.
252-0538-00LShape Modeling and Geometry Processing Information W4 credits2V + 1UO. Sorkine Hornung, D. Panozzo
AbstractThis course covers some of the latest developments in geometric modeling and digital geometry processing. Topics include surface modeling based on triangle meshes, mesh generation, surface reconstruction, mesh fairing and simplification, discrete differential geometry and interactive shape editing.
ObjectiveThe students will learn how to design, program and analyze algorithms and systems for interactive 3D shape modeling and digital geometry processing.
ContentRecent advances in 3D digital geometry processing have created a plenitude of novel concepts for the mathematical representation and interactive manipulation of geometric models. This course covers some of the latest developments in geometric modeling and digital geometry processing. Topics include surface modeling based on triangle meshes, mesh generation, surface reconstruction, mesh fairing and simplification, discrete differential geometry and interactive shape editing.
Lecture notesSlides and course notes
Prerequisites / NoticePrerequisites:
Introduction to Computer Graphics, experience with C++ programming. Some background in geometry or computational geometry is helpful, but not necessary.
252-0570-00LGame Programming Laboratory Information
In the Master Programme max. 10 credits can be accounted by Labs on top of the Interfocus Courses. These Labs will only count towards the Master Programme. Additional Labs will be listed on the Addendum.
W10 credits9PB. Sumner
AbstractThe goal of this course is the in-depth understanding of the technology and programming underlying computer games. Students gradually design and develop a computer game in small groups and get acquainted with the art of game programming.
ObjectiveThe goal of this new course is to acquaint students with the
technology and art of programming modern three-dimensional computer
games.
ContentThis is a new course that addresses modern three-dimensional computer
game technology. During the course, small groups of students will
design and develop a computer game. Focus will be put on technical
aspects of game development, such as rendering, cinematography,
interaction, physics, animation, and AI. In addition, we will
cultivate creative thinking for advanced gameplay and visual effects.

The "laboratory" format involves a practical, hands-on approach with
neither traditional lectures nor exercises. Instead, we will meet
once a week to discuss technical issues and to track progress. We
plan to utilize Microsoft's XNA Game Studio Express, which is a
collection libraries and tools that facilitate game development.
While development will take place on PCs, we will ultimately deploy
our games on the XBox 360 console.

At the end of the course we will present our results to the public.
Lecture notesOnline XNA documentation.
Prerequisites / NoticeThe number of participants is limited.

Prerequisites include:

- good programming skills (Java, C++, C#, etc.)

- CG experience: Students should have taken, at a minimum, Visual
Computing. Higher level courses are recommended, such as Introduction
to Computer Graphics, Surface Representations and Geometric Modeling,
and Physically-based Simulation in Computer Graphics.
252-0579-00L3D Photography Information W4 credits3GM. Pollefeys, T. Sattler
AbstractThe goal of this course is to provide students with a good understanding of how 3D object shape and appearance can be estimated from images and videos. The main concepts and techniques will be studied in depth and practical algorithms and approaches will be discussed and explored through the exercises and a course project.
ObjectiveAfter attending this course students should:
1. Understand the concepts that allow recovering 3D shape from images.
2. Have a good overview of the state of the art in 3D photography
3. Be able to critically analyze and asses current research in the area
4. Implement components of a 3D photography system.
ContentThe course will cover the following topics a.o. camera model and calibration, single-view metrology, triangulation, epipolar and multi-view geometry, two-view and multi-view stereo, structured-light, feature tracking and matching, structure-from-motion, shape-from-silhouettes and 3D modeling and applications.
252-5705-00LImage Synthesis Information W6 credits5GW. Jarosz, W. A. Jakob
AbstractThis course covers advanced topics in rendering and image synthesis.
ObjectiveThe goal is to get a broader knowledge of rendering algorithms and an in-depth understanding of advanced topics in rendering. Students will learn about the principles of how light interacts with a scene, and how to translate the associated image formation problem into efficient rendering algorithms. Since this is an upper-level coarse, a focus is placed on state of the art techniques and recent trends in research.
ContentThis course expands upon the rendering foundation taught in the Computer Graphics course.

We assume a basic knowledge of ray tracing and shading, and expand significantly on the physics of light transport, discuss the rendering equation, and focus significant time on advanced techniques to enhance the realism and lower the computational cost of rendered images.

Starting from a review of the physics underlying a range of complex light transport effects (depth-of-field, soft shadows, global illumination, participating media, subsurface scattering), we discuss how to leverage various mathematical tools (e.g. density estimation, Monte Carlo sampling, Markov Chain Monte Carlo) to obtain a range of state-of-the-art rendering algorithms (including variants of path tracing, photon mapping, and Metropolis light transport).

The course includes a rendering competition where students create a realistic image of their choosing using the rendering software they develop in the course.
LiteratureStudents will read from the course text books, as well as rendering research papers.
Prerequisites / NoticeCalculus and linear algebra, basic concepts of algorithms and data structures, programming skills in C++, Computer Graphics core course, Visual Computing core course
263-3700-00LUser Interface Engineering Information W4 credits2V + 1UO. Hilliges
AbstractAn in-depth introduction to the core concepts of post-desktop user interface engineering. Current topics in UI research, in particular non-desktop based interaction, mobile device interaction, augmented and mixed reality, and advanced sensor and output technologies.
ObjectiveStudents will learn about fundamental aspects pertaining to the design and implementation of modern (non-desktop) user interfaces. Students will understand the basics of human cognition and capabilities as well as gain an overview of technologies for input and output of data. The core competency acquired through this course is a solid foundation in data-driven algorithms to process and interpret human input into computing systems. 

At the end of the course students should be able to understand and apply advanced hardware and software technologies to sense and interpret user input. Students will be able to develop systems that incorporate non-standard sensor and display technologies and will be able to apply data-driven algorithms in order to extract semantic meaning from raw sensor data.
ContentUser Interface Engineering covers theoretical and practical aspects relating to the design and implementation of modern non-standard user interfaces. A particular area of interest are machine-learning based algorithms for input recognition in advanced non-desktop user interfaces, including UIs for mobile devices but also Augmented Reality UIs, gesture and multi-modal user interfaces. 

The course covers three main areas:
I) Basic principles of human cognition and perception (and their application for UIs)
II) (Hardware) technologies for user input sensing
III) Data-driven methods for input recognition (gestures, speech, etc.)

Specific topics include: 
* Model Human Processor (MHP) model - prediction of task completion times.
* Fitts' Law - measure of information load on human motor and cognitive system during user interaction.
* Touch sensor technologies (capacitive, resistive, force sensing etc).
* Data-driven algorithms for user input recognition:
- SVMs for classification and regression
- Randomized Decision Forests for gesture recognition and pose estimation
- Markov chains and HMMs for gesture and speech recognition
- Optical flow and other image processing and computer vision techniques
- Input filtering (Kalman)
* Applications of the above in HCI research
Lecture notesSlides and other materials will be available online. Lecture slides on a particular topic will typically not be made available prior the completion of that lecture.
LiteratureA detailed reading list will be made available on the course website.
Prerequisites / NoticePrerequisites: proficiency in a programming language such as C, programming methodology, problem analysis, program structure, etc. Normally met through an introductory course in programming in C, C++, Java.

The following courses are strongly recommended as prerequisite:
* "Human Computer Interaction"
* "Machine Learning"
* "Visual Computing" or "Computer Vision"

The course will be assessed by a written Midterm and Final examination in English. No course materials or electronic devices can be used during the examination. Note that the examination will be based on the contents of the lectures, the associated reading materials and the exercises.
252-5706-00LMathematical Foundations of Computer Graphics and Vision Information W4 credits2V + 1UJ.‑C. Bazin, C. Öztireli
AbstractThis course presents the fundamental mathematical tools and concepts used in computer graphics and vision. Each theoretical topic is introduced in the context of practical vision or graphic problems, showcasing its importance in real-world applications.
ObjectiveThe main goal is to equip the students with the key mathematical tools necessary to understand state-of-the-art algorithms in vision and graphics. In addition to the theoretical part, the students will learn how to use these mathematical tools to solve a wide range of practical problems in visual computing. After successfully completing this course, the students will be able to apply these mathematical concepts and tools to practical industrial and academic projects in visual computing.
ContentThe theory of each mathematical concept or tool will be introduced and we will then showcase their practical utility in a variety of different applications in computer graphics and vision. The course will cover topics in sampling, reconstruction, optimization, differentiation, quadrature and spectral methods. Applications will include 3D surface reconstruction, structure from motion, camera pose estimation, image editing, character animation, ray tracing, architectural design and shape recognition.
227-1034-00LComputational Vision Information W6 credits2V + 1UD. Kiper, K. A. Martin
AbstractThis course focuses on neural computations that underlie visual perception. We study how visual signals are processed in the retina, LGN and visual cortex. We study the morpholgy and functional architecture of cortical circuits responsible for pattern, motion, color, and three-dimensional vision.
ObjectiveThis course considers the operation of circuits in the process of neural computations. The evolution of neural systems will be considered to demonstrate how neural structures and mechanisms are optimised for energy capture, transduction, transmission and representation of information. Canonical brain circuits will be described as models for the analysis of sensory information. The concept of receptive fields will be introduced and their role in coding spatial and temporal information will be considered. The constraints of the bandwidth of neural channels and the mechanisms of normalization by neural circuits will be discussed.
The visual system will form the basis of case studies in the computation of form, depth, and motion. The role of multiple channels and collective computations for object recognition will
be considered. Coordinate transformations of space and time by cortical and subcortical mechanisms will be analysed. The means by which sensory and motor systems are integrated to allow for adaptive behaviour will be considered.
ContentThis course considers the operation of circuits in the process of neural computations. The evolution of neural systems will be considered to demonstrate how neural structures and mechanisms are optimised for energy capture, transduction, transmission and representation of information. Canonical brain circuits will be described as models for the analysis of sensory information. The concept of receptive fields will be introduced and their role in coding spatial and temporal information will be considered. The constraints of the bandwidth of neural channels and the mechanisms of normalization by neural circuits will be discussed.
The visual system will form the basis of case studies in the computation of form, depth, and motion. The role of multiple channels and collective computations for object recognition will
be considered. Coordinate transformations of space and time by cortical and subcortical mechanisms will be analysed. The means by which sensory and motor systems are integrated to allow for adaptive behaviour will be considered.
LiteratureBooks: (recommended references, not required)
1. An Introduction to Natural Computation, D. Ballard (Bradford Books, MIT Press) 1997.
2. The Handbook of Brain Theorie and Neural Networks, M. Arbib (editor), (MIT Press) 1995.
263-5200-00LData Mining: Learning from Large Data Sets Information
Does not take place this semester.
The course will be offered again in the autumn semester 2015.
W4 credits2V + 1UA. Krause
AbstractMany scientific and commercial applications require insights from massive, high-dimensional data sets. This courses introduces principled, state-of-the-art techniques from statistics, algorithms and discrete and convex optimization for learning from such large data sets. The course both covers theoretical foundations and practical applications.
ObjectiveMany scientific and commercial applications require us to obtain insights from massive, high-dimensional data sets. In this graduate-level course, we will study principled, state-of-the-art techniques from statistics, algorithms and discrete and convex optimization for learning from such large data sets. The course will both cover theoretical foundations and practical applications.
ContentTopics covered:
- Dealing with large data (Data centers; Map-Reduce/Hadoop; Amazon Mechanical Turk)
- Fast nearest neighbor methods (Shingling, locality sensitive hashing)
- Online learning (Online optimization and regret minimization, online convex programming, applications to large-scale Support Vector Machines)
- Multi-armed bandits (exploration-exploitation tradeoffs, applications to online advertising and relevance feedback)
- Active learning (uncertainty sampling, pool-based methods, label complexity)
- Dimension reduction (random projections, nonlinear methods)
- Data streams (Sketches, coresets, applications to online clustering)
- Recommender systems
Prerequisites / NoticePrerequisites: Solid basic knowledge in statistics, algorithms and programming. Background in machine learning is helpful but not required.
  •  Page  1  of  1