Search result: Catalogue data in Autumn Semester 2021
CAS in Computer Science  | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 Focus Courses and Electives | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Number | Title | Type | ECTS | Hours | Lecturers | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 263-4640-00L | Network Security | W | 8 credits | 2V + 2U + 3A | A. Perrig, S. Frei, M. Legner, K. Paterson | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | Some of today's most damaging attacks on computer systems involve exploitation of network infrastructure, either as the target of attack or as a vehicle to attack end systems. This course provides an in-depth study of network attack techniques and methods to defend against them. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | - Students are familiar with fundamental network-security concepts. - Students can assess current threats that Internet services and networked devices face, and can evaluate appropriate countermeasures. - Students can identify and assess vulnerabilities in software systems and network protocols. - Students have an in-depth understanding of a range of important state-of-the-art security technologies. - Students can implement network-security protocols based on cryptographic libraries. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The course will cover topics spanning four broad themes with a focus on the first two themes: (1) network defense mechanisms such as public-key infrastructures, TLS, VPNs, anonymous-communication systems, secure routing protocols, secure DNS systems, and network intrusion-detection systems; (2) network attacks such as hijacking, spoofing, denial-of-service (DoS), and distributed denial-of-service (DDoS) attacks; (3) analysis and inference topics such as traffic monitoring and network forensics; and (4) new technologies related to next-generation networks. In addition, several guest lectures will provide in-depth insights into specific current real-world network-security topics. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | This lecture is intended for students with an interest in securing Internet communication services and network devices. Students are assumed to have knowledge in networking as taught in a communication networks lecture like 252-0064-00L or 227-0120-00L. Basic knowledge of information security or applied cryptography as taught in 252-0211-00L or 263-4660-00L is beneficial, but an overview of the most important cryptographic primitives will be provided at the beginning of the course. The course will involve several graded course projects. Students are expected to be familiar with a general-purpose or network programming language such as C/C++, Go, Python, or Rust. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Competencies |
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-5005-00L | Artificial Intelligence in Education  Number of participants limited to 75. | W | 5 credits | 2V + 1U + 1A | M. Sachan, T. Sinha | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | Artificial Intelligence (AI) methods have shown to have a profound impact in educational technologies, where the great variety of tasks and data types enable us to get benefit of AI techniques in many different ways. We will review relevant methods and applications of AI in various educational technologies, and work on problem sets and projects to solve problems in education with the help of AI. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The course will be centered around exploring methodological and system-focused perspectives on designing AI systems for education and analyzing educational data using AI methods. Students will be expected to a) engage in presentations and active in-class discussion, b) work on problem-sets exemplifying the use of educational data mining techniques, and c) undertake a final course project with feedback from instructors. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The course will start with a general introduction to AI, where we will cover supervised and unsupervised learning techniques (e.g.,classification and regression models, feature selection and preprocessing of data, clustering, dimensionality reduction and text mining techniques) with a focus on application of these techniques in educational data mining. After the introduction of the basic methodologies, we will continue with the most relevant applications of AI in educational technologies (e.g., intelligent tutoring and student personalization, scaffolding open-ended discovery learning, socially-aware AI and learning at scale with AI systems). In the final part of the course, we will cover challenges associated with using AI in student facing settings. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Lecture notes | Lecture slides will be made available at the course Web site. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Literature | No textbook is required, but there will be regularly assigned readings from research literature, linked to the course website. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | There are no prerequisites for this class. However, it will help if the student has taken an undergraduate or graduate level class in statistics, data science or machine learning. This class is appropriate for advanced undergraduates and master students in Computer Science as well as PhD students in other departments. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-5210-00L | Probabilistic Artificial Intelligence | W | 8 credits | 3V + 2U + 2A | A. Krause | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | This course introduces core modeling techniques and algorithms from machine learning, optimization and control for reasoning and decision making under uncertainty, and study applications in areas such as robotics. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | How can we build systems that perform well in uncertain environments? 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 robotics. The course is designed for graduate students. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | Topics covered: - Probability - Probabilistic inference (variational inference, MCMC) - Bayesian learning (Gaussian processes, Bayesian deep learning) - Probabilistic planning (MDPs, POMPDPs) - Multi-armed bandits and Bayesian optimization - Reinforcement learning | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | Solid basic knowledge in statistics, algorithms and programming. The material covered in the course "Introduction to Machine Learning" is considered as a prerequisite. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-5255-00L | Foundations of Reinforcement Learning Number of participants limited to 190. Last cancellation/deregistration date for this graded semester performance: Thursday, 28 October 2021! Please note that after that date no deregistration will be accepted and the course will be considered as "fail". | W | 5 credits | 2V + 2A | N. He | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | Reinforcement learning (RL) has been in the limelight of many recent breakthroughs in artificial intelligence. This course focuses on theoretical and algorithmic foundations of reinforcement learning, through the lens of optimization, modern approximation, and learning theory. The course targets M.S. students with strong research interests in reinforcement learning, optimization, and control. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | This course aims to provide students with an advanced introduction of RL theory and algorithms as well as bring them near the frontier of this active research field. By the end of the course, students will be able to - Identify the strengths and limitations of various reinforcement learning algorithms; - Formulate and solve sequential decision-making problems by applying relevant reinforcement learning tools; - Generalize or discover “new” applications, algorithms, or theories of reinforcement learning towards conducting independent research on the topic. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | Basic topics include fundamentals of Markov decision processes, approximate dynamic programming, linear programming and primal-dual perspectives of RL, model-based and model-free RL, policy gradient and actor-critic algorithms, Markov games and multi-agent RL. If time allows, we will also discuss advanced topics such as batch RL, inverse RL, causal RL, etc. The course keeps strong emphasis on in-depth understanding of the mathematical modeling and theoretical properties of RL algorithms. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Lecture notes | Lecture notes will be posted on Moodle. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Literature | Dynamic Programming and Optimal Control, Vol I & II, Dimitris Bertsekas Reinforcement Learning: An Introduction, Second Edition, Richard Sutton and Andrew Barto. Algorithms for Reinforcement Learning, Csaba Czepesvári. Reinforcement Learning: Theory and Algorithms, Alekh Agarwal, Nan Jiang, Sham M. Kakade. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | Students are expected to have strong mathematical background in linear algebra, probability theory, optimization, and machine learning. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-5902-00L | Computer Vision | W | 8 credits | 3V + 1U + 3A | M. Pollefeys, S. Tang, F. Yu | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | The goal of this course is to provide students with a good understanding of computer vision and image analysis techniques. The main concepts and techniques will be studied in depth and practical algorithms and approaches will be discussed and explored through the exercises. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The objectives of this course are: 1. To introduce the fundamental problems of computer vision. 2. To introduce the main concepts and techniques used to solve those. 3. To enable participants to implement solutions for reasonably complex problems. 4. To enable participants to make sense of the computer vision literature. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | Camera models and calibration, invariant features, Multiple-view geometry, Model fitting, Stereo Matching, Segmentation, 2D Shape matching, Shape from Silhouettes, Optical flow, Structure from motion, Tracking, Object recognition, Object category recognition | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | It is recommended that students have taken the Visual Computing lecture or a similar course introducing basic image processing concepts before taking this course. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-5905-00L | Mixed Reality | W | 5 credits | 3G + 1A | I. Armeni, F. Bogo, M. Pollefeys | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | The goal of this course is an introduction and hands-on experience on latest mixed reality technology at the cross-section of 3D computer graphics and vision, human machine interaction, as well as gaming technology. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | After attending this course, students will: 1. Understand the foundations of 3D graphics, Computer Vision, and Human-Machine Interaction 2. Have a clear understanding on how to build mixed reality apps 3. Have a good overview of state-of-the-art Mixed Reality 4. Be able to critically analyze and asses current research in this area. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The course introduces latest mixed reality technology and provides introductory elements for a number of related fields including: Introduction to Mixed Reality / Augmented Reality / Virtual Reality Introduction to 3D Computer Graphics, 3D Computer Vision. This will take place in the form of short lectures, followed by student presentations discussing the current state-of-the-art. The main focus of this course are student projects on mixed reality topics, where small groups of students will work on a particular project with the goal to design, develop and deploy a mixed reality application. The project topics are flexible and can reach from proof-of-concept vision/graphics/HMI research, to apps that support teaching with interactive augmented reality, or game development. The default platform will be Microsoft HoloLens in combination with C# and Unity3D - other platforms are also possible to use, such as tablets and phones. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | Prerequisites include: - Good programming skills (C# / C++ / Java etc.) - Computer graphics/vision experience: Students should have taken, at a minimum, Visual Computing. Higher level courses are recommended, such as Introduction to Computer Graphics, 3D Vision, Computer Vision. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 636-0007-00L | Computational Systems Biology | W | 6 credits | 3V + 2U | J. Stelling | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | Study of fundamental concepts, models and computational methods for the analysis of complex biological networks. Topics: Systems approaches in biology, biology and reaction network fundamentals, modeling and simulation approaches (topological, probabilistic, stoichiometric, qualitative, linear / nonlinear ODEs, stochastic), and systems analysis (complexity reduction, stability, identification). | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The aim of this course is to provide an introductory overview of mathematical and computational methods for the modeling, simulation and analysis of biological networks. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | Biology has witnessed an unprecedented increase in experimental data and, correspondingly, an increased need for computational methods to analyze this data. The explosion of sequenced genomes, and subsequently, of bioinformatics methods for the storage, analysis and comparison of genetic sequences provides a prominent example. Recently, however, an additional area of research, captured by the label "Systems Biology", focuses on how networks, which are more than the mere sum of their parts' properties, establish biological functions. This is essentially a task of reverse engineering. The aim of this course is to provide an introductory overview of corresponding computational methods for the modeling, simulation and analysis of biological networks. We will start with an introduction into the basic units, functions and design principles that are relevant for biology at the level of individual cells. Making extensive use of example systems, the course will then focus on methods and algorithms that allow for the investigation of biological networks with increasing detail. These include (i) graph theoretical approaches for revealing large-scale network organization, (ii) probabilistic (Bayesian) network representations, (iii) structural network analysis based on reaction stoichiometries, (iv) qualitative methods for dynamic modeling and simulation (Boolean and piece-wise linear approaches), (v) mechanistic modeling using ordinary differential equations (ODEs) and finally (vi) stochastic simulation methods. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Lecture notes | http://www.csb.ethz.ch/education/lectures.html | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Literature | U. Alon, An introduction to systems biology. Chapman & Hall / CRC, 2006. Z. Szallasi et al. (eds.), System modeling in cellular biology. MIT Press, 2010. B. Ingalls, Mathematical modeling in systems biology: an introduction. MIT Press, 2013 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 636-0017-00L | Computational Biology | W | 6 credits | 3G + 2A | T. Vaughan | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | The aim of the course is to provide up-to-date knowledge on how we can study biological processes using genetic sequencing data. Computational algorithms extracting biological information from genetic sequence data are discussed, and statistical tools to understand this information in detail are introduced. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | Attendees will learn which information is contained in genetic sequencing data and how to extract information from this data using computational tools. The main concepts introduced are: * stochastic models in molecular evolution * phylogenetic & phylodynamic inference * maximum likelihood and Bayesian statistics Attendees will apply these concepts to a number of applications yielding biological insight into: * epidemiology * pathogen evolution * macroevolution of species | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The course consists of four parts. We first introduce modern genetic sequencing technology, and algorithms to obtain sequence alignments from the output of the sequencers. We then present methods for direct alignment analysis using approaches such as BLAST and GWAS. Second, we introduce mechanisms and concepts of molecular evolution, i.e. we discuss how genetic sequences change over time. Third, we employ evolutionary concepts to infer ancestral relationships between organisms based on their genetic sequences, i.e. we discuss methods to infer genealogies and phylogenies. Lastly, we introduce the field of phylodynamics, the aim of which is to understand and quantify population dynamic processes (such as transmission in epidemiology or speciation & extinction in macroevolution) based on a phylogeny. Throughout the class, the models and methods are illustrated on different datasets giving insight into the epidemiology and evolution of a range of infectious diseases (e.g. HIV, HCV, influenza, Ebola). Applications of the methods to the field of macroevolution provide insight into the evolution and ecology of different species clades. Students will be trained in the algorithms and their application both on paper and in silico as part of the exercises. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Lecture notes | Lecture slides will be available on moodle. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Literature | The course is not based on any of the textbooks below, but they are excellent choices as accompanying material: * Yang, Z. 2006. Computational Molecular Evolution. * Felsenstein, J. 2004. Inferring Phylogenies. * Semple, C. & Steel, M. 2003. Phylogenetics. * Drummond, A. & Bouckaert, R. 2015. Bayesian evolutionary analysis with BEAST. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | Basic knowledge in linear algebra, analysis, and statistics will be helpful. Programming in R will be required for the project work (compulsory continuous performance assessments). We provide an R tutorial and help sessions during the first two weeks of class to learn the required skills. However, in case you do not have any previous experience with R, we strongly recommend to get familiar with R prior to the semester start. For the D-BSSE students, we highly recommend the voluntary course „Introduction to Programming“, which takes place at D-BSSE from Wednesday, September 12 to Friday, September 14, i.e. BEFORE the official semester starting date http://www.cbb.ethz.ch/news-events.html For the Zurich-based students without R experience, we recommend the R course Link, or working through the script provided as part of this R course. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Seminars | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Number | Title | Type | ECTS | Hours | Lecturers | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 252-3811-00L | Case Studies from Practice Seminar Number of participants limited to 24. The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | W | 4 credits | 2S | M. Brandis | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | Participants will learn how to analyze and solve IT problems in practice in a systematic way, present findings to decision bodies, and defend their conclusions. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | Participants understand the different viewpoints for IT-decisions in practice, including technical and business aspects, can effectively analyze IT questions from the different viewpoints and facilitate decision making. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | Participants learn how to systematically approach an IT problem in practice. They work in groups of three to solve a case from a participating company in depth, studying provided materials, searching for additional information, analyzing all in depth, interviewing members from the company or discussing findings with them to obtain further insights, and presenting and defending their conclusion to company representatives, the lecturer, and all other participants of the seminar. Participants also learn how to challenge presentations from other teams, and obtain an overview of learnings from the cases other teams worked on. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Lecture notes | Methodologies to analyze the cases and create final presentations. Short overview of each case. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | Successful completion of Lecture "Case Studies from Practice". | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 252-4601-00L | Current Topics in Information Security Number of participants limited to 24. The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | W | 2 credits | 2S | S. Capkun, K. Paterson, A. Perrig, S. Shinde | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | The seminar covers various topics in information security: security protocols (models, specification & verification), trust management, access control, non-interference, side-channel attacks, identity-based cryptography, host-based attack detection, anomaly detection in backbone networks, key-management for sensor networks. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The main goals of the seminar are the independent study of scientific literature and assessment of its contributions as well as learning and practicing presentation techniques. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The seminar covers various topics in information security, including network security, cryptography and security protocols. The participants are expected to read a scientific paper and present it in a 35-40 min talk. At the beginning of the semester a short introduction to presentation techniques will be given. Selected Topics - security protocols: models, specification & verification - trust management, access control and non-interference - side-channel attacks - identity-based cryptography - host-based attack detection - anomaly detection in backbone networks - key-management for sensor networks | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Literature | The reading list will be published on the course web site. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 252-5051-00L | Advanced Topics in Machine Learning Number of participants limited to 40. The deadline for deregistering expires at the end of the fourth week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | W | 2 credits | 2S | J. M. Buhmann, R. Cotterell, J. Vogt, F. Yang | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | 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. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The seminar "Advanced Topics in Machine Learning" familiarizes students with recent developments in pattern recognition and machine learning. Original articles have to be presented and critically reviewed. The students will learn how to structure a scientific presentation in English which covers the key ideas of a scientific paper. An important goal of the seminar presentation is to summarize the essential ideas of the paper in sufficient depth while omitting details which are not essential for the understanding of the work. The presentation style will play an important role and should reach the level of professional scientific presentations. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The seminar will cover a number of recent papers which have emerged as important contributions to the pattern recognition and machine learning literature. The topics will vary from year to year but they are centered on methodological issues in machine learning like new learning algorithms, ensemble methods or new statistical models for machine learning applications. Frequently, papers are selected from computer vision or bioinformatics - two fields, which relies more and more on machine learning methodology and statistical models. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Literature | The papers will be presented in the first session of the seminar. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 252-5701-00L | Advanced Topics in Computer Graphics and Vision Number of participants limited to 24. The deadline for deregistering expires at the end of the third week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | W | 2 credits | 2S | M. Pollefeys, O. Sorkine Hornung, S. Tang | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | This seminar covers advanced topics in computer graphics, such as modeling, rendering, animation, real-time graphics, physical simulation, and computational photography. Each time the course is offered, a collection of research papers is selected and each student presents one paper to the class and leads a discussion about the paper and related topics. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The goal is to get an in-depth understanding of actual problems and research topics in the field of computer graphics as well as improve presentations and critical analysis skills. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | This seminar covers advanced topics in computer graphics, including both seminal research papers as well as the latest research results. Each time the course is offered, a collection of research papers are selected covering topics such as modeling, rendering, animation, real-time graphics, physical simulation, and computational photography. Each student presents one paper to the class and leads a discussion about the paper and related topics. All students read the papers and participate in the discussion. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Lecture notes | no script | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Literature | Individual research papers are selected each term. See http://graphics.ethz.ch/ for the current list. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-2100-00L | Research Topics in Software Engineering Number of participants limited to 22. The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | W | 2 credits | 2S | P. Müller, M. Püschel | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | This seminar is an opportunity to become familiar with current research in software engineering and more generally with the methods and challenges of scientific research. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | Each student will be asked to study some papers from the recent software engineering literature and review them. This is an exercise in critical review and analysis. Active participation is required (a presentation of a paper as well as participation in discussions). | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The aim of this seminar is to introduce students to recent research results in the area of programming languages and software engineering. To accomplish that, students will study and present research papers in the area as well as participate in paper discussions. The papers will span topics in both theory and practice, including papers on program verification, program analysis, testing, programming language design, and development tools. A particular focus will be on domain-specific languages. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Literature | The publications to be presented will be announced on the seminar home page at least one week before the first session. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | Organizational note: the seminar will meet only when there is a scheduled presentation. Please consult the seminar's home page for information. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-3504-00L | Hardware Acceleration for Data Processing Number of participants limited to 24. The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | W | 2 credits | 2S | G. Alonso | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | The seminar will cover topics related to data processing using new hardware in general and hardware accelerators (GPU, FPGA, specialized processors) in particular. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The seminar will cover topics related to data processing using new hardware in general and hardware accelerators (GPU, FPGA, specialized processors) in particular. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The general application areas are big data and machine learning. The systems covered will include systems from computer architecture, high performance computing, data appliances, and data centers. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | Students taking this seminar should have the necessary background in systems and low level programming. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-5156-00L | Beyond iid Learning: Causality, Dynamics, and Interactions Number of participants limited to 60. The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | W | 2 credits | 2S | M. Mühlebach, A. Krause, B. Schölkopf | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | Many machine learning problems go beyond supervised learning on independent data points and require an understanding of the underlying causal mechanisms, the interactions between the learning algorithms and their environment, and adaptation to temporal changes. The course highlights some of these challenges and relates them to state-of-the-art research. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The goal of this seminar is to gain experience with machine learning research and foster interdisciplinary thinking. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The seminar will be divided into two parts. The first part summarizes the basics of statistical learning theory, game theory, causal inference, and dynamical systems in four lectures. This sets the stage for the second part, where distinguished speakers will present selected aspects in greater detail and link them to their current research. Keywords: Causal inference, adaptive decision-making, reinforcement learning, game theory, meta learning, interactions with humans. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Lecture notes | Further information will be published on the course website: https://beyond-iid-learning.xyz/ | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | BSc in computer science or related field (engineering, physics, mathematics). Passed at least one learning course, such as ``Introduction to Machine Learning" or ``Probabilistic Artificial Intelligence". | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 263-3713-00L | Advanced Topics in Human-Centric Computer Vision Numbers of participants limited to 20. The deadline for deregistering expires at the end of the third week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar. | W | 2 credits | 2S | O. Hilliges | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract | In this seminar we will discuss state-of-the-art literature on human-centric computer vision topics including but not limited to human pose estimation, hand and eye-gaze estimation as well as generative modeliing of detailed human activities. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The learning objective is to analyze selected research papers published at top computer vision and machine learning venues. A key focus will be placed on identifying and discussing open problems and novel solutions in this space. The seminar will achieve this via several components: reading papers, technical presentations, writing analysis and critique summaries, class discussions, and exploration of potential research topics. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Content | The goal of the seminar is not only to familiarize students with exciting new research topics, but also to teach basic scientific writing and oral presentation skills. The seminar will have a different structure from regular seminars to encourage more discussion and a deeper learning experience. We will treat papers as case studies and discuss them in-depth in the seminar. Once per semester, every student will have to take one of the following roles: Presenter: Give a presentation about the paper that you read in depth. Reviewer: Perform a critical review of the paper. All other students: read the paper and submit questions they have about the paper before the presentation. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | Participation will be limited subject to available topics. Furthermore, students will have to submit a motivation paragraph. Participants will be selected based on this paragraph. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Competencies |
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Page
2
of
2
All