Suchergebnis: Katalogdaten im Herbstsemester 2017

Informatik Master Information
Vertiefungsfächer
Vertiefung in Visual Computing
Wahlfächer der Vertiefung in Visual Computing
NummerTitelTypECTSUmfangDozierende
252-0543-01LComputer Graphics Information W6 KP3V + 2UM. Gross, J. Novak
KurzbeschreibungThis course covers some of the fundamental concepts of computer graphics, namely 3D object representations and generation of photorealistic images from digital representations of 3D scenes.
LernzielAt the end of the course the students will be able to build a rendering system. The students will study the basic principles of rendering and image synthesis. In addition, the course is intended to stimulate the students' curiosity to explore the field of computer graphics in subsequent courses or on their own.
InhaltThis course covers fundamental concepts of modern computer graphics. Students will learn about 3D object representations and the details of how to generate photorealistic images from digital representations of 3D scenes. Starting with an introduction to 3D shape modeling and representation, texture mapping and ray-tracing, we will move on to acceleration structures, the physics of light transport, appearance modeling and global illumination principles and algorithms. We will end with an overview of modern image-based image synthesis techniques, covering topics such as lightfields and depth-image based rendering.
Skriptno
Voraussetzungen / BesonderesPrerequisites:
Fundamentals of calculus and linear algebra, basic concepts of algorithms and data structures, programming skills in C++, Visual Computing course recommended.
The programming assignments will be in C++. This will not be taught in the class.
252-0546-00LPhysically-Based Simulation in Computer Graphics Information W4 KP2V + 1UM. Bächer, V. da Costa de Azevedo
KurzbeschreibungDie Vorlesung gibt eine Einführung in das Gebiet der physikalisch basierten Animation in der Computer Graphik und einen Überblick über fundamentale Methoden und Algorithmen. In den praktischen Übungen werden drei Aufgabenblätter in kleinen Gruppen bearbeitet. Zudem sollen in einem Programmierprojekt die Vorlesungsinhalte in einem 3D Spiel oder einer vergleichbaren Anwendung umgesetzt werden.
LernzielDie Vorlesung gibt eine Einführung in das Gebiet der physikalisch basierten Animation in der Computer Graphik und einen Überblick über fundamentale Methoden und Algorithmen. In den praktischen Übungen werden drei Aufgabenblätter in kleinen Gruppen bearbeitet. Zudem sollen in einem Programmierprojekt die Vorlesungsinhalte in einem 3D Spiel oder einer vergleichbaren Anwendung umgesetzt werden.
InhaltIn der Vorlesung werden Themen aus dem Gebiet der physikalisch-basierten Modellierung wie Partikel-Systeme, Feder-Masse Modelle, die Methoden der Finiten Differenzen und der Finiten Elemente behandelt. Diese Methoden und Techniken werden verwendet um deformierbare Objekte oder Flüssigkeiten zu simulieren mit Anwendungen in Animationsfilmen, 3D Computerspielen oder medizinischen Systemen. Es werden auch Themen wie Starrkörperdynamik, Kollisionsdetektion und Charakteranimation behandelt.
Voraussetzungen / BesonderesBasiskenntnisse in Analysis und Physik, Algorithmen und Datenstrukturen und der Programmierung in C++. Kenntnisse auf den Gebieten Numerische Mathematik sowie Gewoehnliche und Partielle Differentialgleichungen sind von Vorteil, werden aber nicht vorausgesetzt.
263-2400-00LReliable and Interpretable Artificial Intelligence Information W4 KP2V + 1UM. Vechev
KurzbeschreibungCreating reliable and explainable probabilistic models is a major challenge to solving the artificial intelligence problem. This course covers some of the latest advances that bring us closer to constructing such models. These advances span the areas of program synthesis/induction, programming languages, machine learning, and probabilistic programming.
LernzielThe main objective of this course is to expose students to the latest and most exciting research in the area of explainable and interpretable artificial intelligence, a topic of fundamental and increasing importance. Upon completion of the course, the students should have mastered the underlying methods and be able to apply them to a variety of problems.
InhaltThe material draws on some of the latest research advances in several areas of computer science: program synthesis/induction, programming languages, deep learning, and probabilistic programming.

The material consists of three interconnected parts:

Part I: Program Synthesis/Induction
----------------------------------------

Synthesis is a new frontier in AI where the computer programs itself from user provided examples. Synthesis has significant applications for non-programmers as well as for programmers where it can provide massive productivity increase (e.g., wrangling for data scientists). Modern synthesis techniques excel at learning functions over discrete spaces from (partial) intent. There have been a number of recent, exciting breakthroughs in techniques that discover complex, interpretable/explainable functions from few examples, partial sketches and other forms of supervision.

Topics covered:

- Theory of program synthesis: version spaces, counter-example guided inductive synthesis (CEGIS) with SAT/SMT, synthesis from noisy examples, learning with few examples, compositional synthesis, lower bounds on learning.

- Applications of techniques: synthesis for end users (e.g., spreadsheets), data analytics and financial computing, interpretable machine learning models for structured data.

- Combining neural networks and synthesis

Part II: Robustness of Deep Learning
-----------------------------------------

Deep learning methods based on neural networks have made impressive advances in recent years. A fundamental challenge with these models is that of understanding what the trained neural network has actually learned, for example, how stable / robust the network is to slight variations of the input (e.g., an image or a video), how easy it is to fool the network into mis-classifying obvious inputs, etc.

Topics covered:

- Basics of neural networks: fully connected, convolutional networks, residual networks, activation functions

- Finding adversarial examples in deep learning with SMT

- Methods and tools to guarantee robustness of deep nets (e.g., via affine arithmetic, SMT solvers); synthesis of robustness specs


Part III: Probabilistic Programming
--------------------------------------

Probabilistic programming is an emerging direction whose goal is democratize the construction of probabilistic models. In probabilistic programming, the user specifies a model while inference is left to the underlying solver. The idea is that the higher level of abstraction makes it easier to express, understand and reason about probabilistic models.

Topics covered:

- Inference: MCMC samplers and tactics (approximate), symbolic inference (exact).

- Semantics: basic measure theoretic semantics of probability; bridging measure theory and symbolic inference.

- Frameworks and languages: WebPPL (MIT/Stanford), PSI (ETH), Picture/Venture (MIT), Anglican (Oxford).

- Synthesis for probabilistic programs: this connects to Part I

- Applications of probabilistic programming: using the above solvers for reasoning about bias in machine learning models (connects to Part II), reasoning about computer networks, security protocols, approximate computing, cognitive models, rational agents.
263-3300-00LData Science Lab Information Belegung eingeschränkt - Details anzeigen
Maximale Teilnehmerzahl: 30.

Im Masterstudium können zusätzlich zu den Vertiefungsübergreifenden Fächern nur max. 10 Kreditpunkte über Laboratorien erarbeitet werden. Weitere Laboratorien werden auf dem Beiblatt aufgeführt.
W10 KP9PC. Zhang, K. Schawinski
KurzbeschreibungIn this class, we bring together data science applications
provided by ETH researchers outside computer science and
teams of computer science master's students. Two to three
students will form a team working on data science/machine
learning-related research topics provided by scientists in
a diverse range of domains such as astronomy, biology,
social sciences etc.
LernzielThe goal of this class if for students to gain experience
of dealing with data science and machine learning applications
"in the wild". Students are expected to go through the full
process starting from data cleaning, modeling, execution,
debugging, error analysis, and quality/performance refinement.

Website: Link
Voraussetzungen / BesonderesEach student is required to send the lecturer their CV
and transcript and the lecturer will decide the enrollment
on a per-student basis. Moreover, the students are expected
to have experience about machine learning and deep learning.

EMAIL to send CV: Link
263-5200-00LData Mining: Learning from Large Data Sets Information W4 KP2V + 1UA. Krause, Y. Levy
KurzbeschreibungMany 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.
LernzielMany 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.
InhaltTopics 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
Voraussetzungen / BesonderesPrerequisites: Solid basic knowledge in statistics, algorithms and programming. Background in machine learning is helpful but not required.
263-5210-00LProbabilistic Artificial Intelligence Information W4 KP2V + 1UA. Krause
KurzbeschreibungThis course introduces core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as sensor networks, robotics, and the Internet.
LernzielHow can we build systems that perform well in uncertain environments and unforeseen situations? How can we develop systems that exhibit "intelligent" behavior, without prescribing explicit rules? How can we build systems that learn from experience in order to improve their performance? We will study core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as sensor networks, robotics, and the Internet. The course is designed for upper-level undergraduate and graduate students.
InhaltTopics covered:
- Search (BFS, DFS, A*), constraint satisfaction and optimization
- Tutorial in logic (propositional, first-order)
- Probability
- Bayesian Networks (models, exact and approximative inference, learning) - Temporal models (Hidden Markov Models, Dynamic Bayesian Networks)
- Probabilistic palnning (MDPs, POMPDPs)
- Reinforcement learning
- Combining logic and probability
Voraussetzungen / BesonderesSolid basic knowledge in statistics, algorithms and programming
263-5701-00LVisualization Information W4 KP2V + 1UT. Günther
KurzbeschreibungThis lecture provides an introduction into visualization of scientific and abstract data.
LernzielThe lecture introduces into the two main branches of visualization: scientific visualization and information visualization. The focus is set onto scientific data, demonstrating the usefulness and necessity of computer graphics in other fields than the entertainment industry. The exercises are mainly theoretical, practicing the mathematical foundations such as numerical integration, differential vector calculus, and flow field analysis.
InhaltThis lecture opens with human cognition basics, and scalar and vector calculus. Afterwards, this is applied to the visualization of air and fluid flows, including geometry-based, topology-based and feature-based methods. Further, the direct and indirect visualization of volume data is discussed. The lecture ends on the viualization of abstract, non-spatial and multi-dimensional data by means of information visualization.
Voraussetzungen / BesonderesFundamentals of differential calculus. Knowledge on numerical mathematics, computer algebra systems, as well as ordinary and partial differential equations is an asset, but not required.
  •  Seite  1  von  1