Search result: Catalogue data in Autumn Semester 2021
CAS in Computer Science | ||||||||||||
Focus Courses and Electives | ||||||||||||
Number | Title | Type | ECTS | Hours | Lecturers | |||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
252-0237-00L | Concepts of Object-Oriented Programming | W | 8 credits | 3V + 2U + 2A | P. Müller | |||||||
Abstract | Course that focuses on an in-depth understanding of object-oriented programming and compares designs of object-oriented programming languages. Topics include different flavors of type systems, inheritance models, encapsulation in the presence of aliasing, object and class initialization, program correctness, reflection | |||||||||||
Learning objective | After this course, students will: Have a deep understanding of advanced concepts of object-oriented programming and their support through various language features. Be able to understand language concepts on a semantic level and be able to compare and evaluate language designs. Be able to learn new languages more rapidly. Be aware of many subtle problems of object-oriented programming and know how to avoid them. | |||||||||||
Content | The main goal of this course is to convey a deep understanding of the key concepts of sequential object-oriented programming and their support in different programming languages. This is achieved by studying how important challenges are addressed through language features and programming idioms. In particular, the course discusses alternative language designs by contrasting solutions in languages such as C++, C#, Eiffel, Java, Python, and Scala. The course also introduces novel ideas from research languages that may influence the design of future mainstream languages. The topics discussed in the course include among others: The pros and cons of different flavors of type systems (for instance, static vs. dynamic typing, nominal vs. structural, syntactic vs. behavioral typing) The key problems of single and multiple inheritance and how different languages address them Generic type systems, in particular, Java generics, C# generics, and C++ templates The situations in which object-oriented programming does not provide encapsulation, and how to avoid them The pitfalls of object initialization, exemplified by a research type system that prevents null pointer dereferencing How to maintain the consistency of data structures | |||||||||||
Literature | Will be announced in the lecture. | |||||||||||
Prerequisites / Notice | Prerequisites: Mastering at least one object-oriented programming language (this course will NOT provide an introduction to object-oriented programming); programming experience | |||||||||||
252-0293-00L | Wireless Networking and Mobile Computing | W | 4 credits | 2V + 1U | S. Mangold | |||||||
Abstract | This course gives an overview about wireless standards and summarizes the state of art for Wi-Fi 802.11, Cellular 5G, and Internet-of-Things, including new topics such as contact tracing with Bluetooth, audio communication, cognitive radio, visible light communications. The course combines lectures with a set of assignments in which students are asked to work with a JAVA simulation tool. | |||||||||||
Learning objective | The objective of the course is to learn about the general principles of wireless communications, including physics, frequency spectrum regulation, and standards. Further, the most up-to-date standards and protocols used for wireless LAN IEEE 802.11, Wi-Fi, Internet-of-Things, sensor networks, cellular networks, visible light communication, and cognitive radios, are analyzed and evaluated. Students develop their own add-on mobile computing algorithms to improve the behavior of the systems, using a Java-based event-driven simulator. We also hand out embedded systems that can be used for experiments for optical communication. | |||||||||||
Content | New: Starting 2020, we will address contact tracing, radio link budget, location distance measurements, and Bluetooth in more depth. Wireless Communication, Wi-Fi, Contact Tracing, Bluetooth, Internet-of-Things, 5G, Standards, Regulation, Algorithms, Radio Spectrum, Cognitive Radio, Mesh Networks, Optical Communication, Visible Light Communication | |||||||||||
Lecture notes | The course material will be made available by the lecturer. | |||||||||||
Literature | (1) The course webpage (look for Stefan Mangold's site) (2) The Java 802 protocol emulator "JEmula802" from https://bitbucket.org/lfield/jemula802 (3) WALKE, B. AND MANGOLD, S. AND BERLEMANN, L. (2006) IEEE 802 Wireless Systems Protocols, Multi-Hop Mesh/Relaying, Performance and Spectrum Coexistence. New York U.S.A.: John Wiley & Sons. Nov 2006. (4) BERLEMANN, L. AND MANGOLD, S. (2009) Cognitive Radio for Dynamic Spectrum Access . New York U.S.A.: John Wiley & Sons. Jan 2009. (5) MANGOLD, S. ET.AL. (2003) Analysis of IEEE 802.11e for QoS Support in Wireless LANs. IEEE Wireless Communications, vol 10 (6), 40-50. | |||||||||||
Prerequisites / Notice | Students should have interest in wireless communication, and should be familiar with Java programming. Experience with GNU Octave or Matlab will help too (not required). | |||||||||||
252-0417-00L | Randomized Algorithms and Probabilistic Methods | W | 10 credits | 3V + 2U + 4A | A. Steger | |||||||
Abstract | Las Vegas & Monte Carlo algorithms; inequalities of Markov, Chebyshev, Chernoff; negative correlation; Markov chains: convergence, rapidly mixing; generating functions; Examples include: min cut, median, balls and bins, routing in hypercubes, 3SAT, card shuffling, random walks | |||||||||||
Learning objective | After this course students will know fundamental techniques from probabilistic combinatorics for designing randomized algorithms and will be able to apply them to solve typical problems in these areas. | |||||||||||
Content | Randomized Algorithms are algorithms that "flip coins" to take certain decisions. This concept extends the classical model of deterministic algorithms and has become very popular and useful within the last twenty years. In many cases, randomized algorithms are faster, simpler or just more elegant than deterministic ones. In the course, we will discuss basic principles and techniques and derive from them a number of randomized methods for problems in different areas. | |||||||||||
Lecture notes | Yes. | |||||||||||
Literature | - Randomized Algorithms, Rajeev Motwani and Prabhakar Raghavan, Cambridge University Press (1995) - Probability and Computing, Michael Mitzenmacher and Eli Upfal, Cambridge University Press (2005) | |||||||||||
252-0463-00L | Security Engineering | W | 7 credits | 2V + 2U + 2A | S. Krstic | |||||||
Abstract | Subject of the class are engineering techniques for developing secure systems. We examine concepts, methods and tools, applied within the different activities of the SW development process to improve security of the system. Topics: security requirements&risk analysis, system modeling&model-based development methods, implementation-level security, and evaluation criteria for secure systems | |||||||||||
Learning objective | Security engineering is an evolving discipline that unifies two important areas: software engineering and security. Software Engineering addresses the development and application of methods for systematically developing, operating, and maintaining, complex, high-quality software. Security, on the other hand, is concerned with assuring and verifying properties of a system that relate to confidentiality, integrity, and availability of data. The goal of this class is to survey engineering techniques for developing secure systems. We will examine concepts, methods, and tools that can be applied within the different activities of the software development process, in order to improve the security of the resulting systems. Topics covered include * security requirements & risk analysis, * system modeling and model-based development methods, * implementation-level security, and * evaluation criteria for the development of secure systems | |||||||||||
Content | Security engineering is an evolving discipline that unifies two important areas: software engineering and security. Software Engineering addresses the development and application of methods for systematically developing, operating, and maintaining, complex, high-quality software. Security, on the other hand, is concerned with assuring and verifying properties of a system that relate to confidentiality, integrity, and availability of data. The goal of this class is to survey engineering techniques for developing secure systems. We will examine concepts, methods, and tools that can be applied within the different activities of the software development process, in order to improve the security of the resulting systems. Topics covered include * security requirements & risk analysis, * system modeling and model-based development methods, * implementation-level security, and * evaluation criteria for the development of secure systems Modules taught: 1. Introduction - Introduction of Infsec group and speakers - Security meets SW engineering: an introduction - The activities of SW engineering, and where security fits in - Overview of this class 2. Requirements Engineering: Security Requirements and some Analysis - Overview: functional and non-functional requirements - Use cases, misuse cases, sequence diagrams - Safety and security 3. Modeling in the design activities - Structure, behavior, and data flow - Class diagrams, statecharts 4. Model-driven security for access control (Part I) - SecureUML as a language for access control - Combining Design Modeling Languages with SecureUML - Semantics, i.e., what does it all mean, - Generation - Examples and experience 5. Model-driven security (Part II) - Continuation of above topics 6. Security patterns (design and implementation) 7. Implementation-level security - Buffer overflows - Input checking - Injection attacks 8. Code scanning - Static code analysis basics - Theoretical and practical challenges - Analysis algorithms - Common bug pattern search and specification - Dataflow analysis 9. Testing - Overview and basics - Model-based testing - Testing security properties 10. Risk analysis and management - "Risk": assets, threats, vulnerabilities, risk - Risk assessment: quantitative and qualitative - Safeguards - Generic risk analysis procedure - The OCTAVE approach - Example of qualitative risk assessment 11. Threat modeling - Overview - Safety engineering basics: FMEA and FTA - Security impact analysis in the design phase - Modeling security threats: attack trees - Examples and experience 12. Evaluation criteria - NIST special papers - ISO/IEC 27000 - Common criteria - BSI baseline protection 13. Guest lecture - TBA | |||||||||||
Literature | - Ross Anderson: Security Engineering, Wiley, 2001. - Matt Bishop: Computer Security, Pearson Education, 2003. - Ian Sommerville: Software Engineering, 6th ed., Addison-Wesley, 2001. - John Viega, Gary McGraw: Building Secure Software, Addison-Wesley, 2002. - Further relevant books and journal/conference articles will be announced in the lecture. | |||||||||||
Prerequisites / Notice | Prerequisite: Class on Information Security | |||||||||||
252-0535-00L | Advanced Machine Learning | W | 10 credits | 3V + 2U + 4A | J. M. Buhmann, C. Cotrini Jimenez | |||||||
Abstract | Machine learning algorithms provide analytical methods to search data sets for characteristic patterns. Typical tasks include the classification of data, function fitting and clustering, with applications in image and speech analysis, bioinformatics and exploratory data analysis. This course is accompanied by practical machine learning projects. | |||||||||||
Learning objective | Students will be familiarized with advanced concepts and algorithms for supervised and unsupervised learning; reinforce the statistics knowledge which is indispensible to solve modeling problems under uncertainty. Key concepts are the generalization ability of algorithms and systematic approaches to modeling and regularization. Machine learning projects will provide an opportunity to test the machine learning algorithms on real world data. | |||||||||||
Content | The theory of fundamental machine learning concepts is presented in the lecture, and illustrated with relevant applications. Students can deepen their understanding by solving both pen-and-paper and programming exercises, where they implement and apply famous algorithms to real-world data. Topics covered in the lecture include: Fundamentals: What is data? Bayesian Learning Computational learning theory Supervised learning: Ensembles: Bagging and Boosting Max Margin methods Neural networks Unsupservised learning: Dimensionality reduction techniques Clustering Mixture Models Non-parametric density estimation Learning Dynamical Systems | |||||||||||
Lecture notes | No lecture notes, but slides will be made available on the course webpage. | |||||||||||
Literature | C. Bishop. Pattern Recognition and Machine Learning. Springer 2007. R. Duda, P. Hart, and D. Stork. Pattern Classification. John Wiley & Sons, second edition, 2001. T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning: Data Mining, Inference and Prediction. Springer, 2001. L. Wasserman. All of Statistics: A Concise Course in Statistical Inference. Springer, 2004. | |||||||||||
Prerequisites / Notice | The course requires solid basic knowledge in analysis, statistics and numerical methods for CSE as well as practical programming experience for solving assignments. Students should have followed at least "Introduction to Machine Learning" or an equivalent course offered by another institution. PhD students are required to obtain a passing grade in the course (4.0 or higher based on project and exam) to gain credit points. | |||||||||||
252-0543-01L | Computer Graphics Does not take place this semester. | W | 8 credits | 3V + 2U + 2A | ||||||||
Abstract | This course covers some of the fundamental concepts of computer graphics generation of photorealistic images from digital representations of 3D scenes and image-based methods for recovering digital scene representations from captured images. | |||||||||||
Learning objective | At 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. | |||||||||||
Content | This 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, geometry representation and texture mapping, we will move on to the physics of light transport, acceleration structures, appearance modeling and Monte Carlo integration. We will apply these principles for computing light transport of direct and global illumination due to surfaces and participating media. We will end with an overview of modern image-based capture and image synthesis methods, covering topics such as geometry and material capture, light-fields and depth-image based rendering. | |||||||||||
Lecture notes | no | |||||||||||
Literature | Books: High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting Multiple view geometry in computer vision Physically Based Rendering: From Theory to Implementation | |||||||||||
Prerequisites / Notice | Prerequisites: 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. | |||||||||||
252-0546-00L | Physically-Based Simulation in Computer Graphics | W | 5 credits | 2V + 1U + 1A | V. da Costa de Azevedo, B. Solenthaler, B. Thomaszewski | |||||||
Abstract | This lecture provides an introduction to physically-based animation in computer graphics and gives an overview of fundamental methods and algorithms. The practical exercises include three assignments which are to be solved in small groups. In an addtional course project, topics from the lecture will be implemented into a 3D game or a comparable application. | |||||||||||
Learning objective | This lecture provides an introduction to physically-based animation in computer graphics and gives an overview of fundamental methods and algorithms. The practical exercises include three assignments which are to be solved in small groups. In an addtional course project, topics from the lecture will be implemented into a 3D game or a comparable application. | |||||||||||
Content | The lecture covers topics in physically-based modeling, such as particle systems, mass-spring models, finite difference and finite element methods. These approaches are used to represent and simulate deformable objects or fluids with applications in animated movies, 3D games and medical systems. Furthermore, the lecture covers topics such as rigid body dynamics, collision detection, and character animation. | |||||||||||
Prerequisites / Notice | Fundamentals of calculus and physics, basic concepts of algorithms and data structures, basic programming skills in C++. Knowledge on numerical mathematics as well as ordinary and partial differential equations is an asset, but not required. | |||||||||||
252-1407-00L | Algorithmic Game Theory | W | 7 credits | 3V + 2U + 1A | P. Penna | |||||||
Abstract | Game theory provides a formal model to study the behavior and interaction of self-interested users and programs in large-scale distributed computer systems without central control. The course discusses algorithmic aspects of game theory. | |||||||||||
Learning objective | Learning the basic concepts of game theory and mechanism design, acquiring the computational paradigm of self-interested agents, and using these concepts in the computational and algorithmic setting. | |||||||||||
Content | The Internet is a typical example of a large-scale distributed computer system without central control, with users that are typically only interested in their own good. For instance, they are interested in getting high bandwidth for themselves, but don't care about others, and the same is true for computational load or download rates. Game theory provides a mathematical model for the behavior and interaction of such selfish users and programs. Classic game theory dates back to the 1930s and typically does not consider algorithmic aspects at all. Only a few years back, algorithms and game theory have been considered together, in an attempt to reconcile selfish behavior of independent agents with the common good. This course discusses algorithmic aspects of game-theoretic models, with a focus on recent algorithmic and mathematical developments. Rather than giving an overview of such developments, the course aims to study selected important topics in depth. Outline: - Introduction to classic game-theoretic concepts. - Existence of stable solutions (equilibria), algorithms for computing equilibria, computational complexity. - Speed of convergence of natural game playing dynamics such as best-response dynamics or regret minimization. - Techniques for bounding the quality-loss due to selfish behavior versus optimal outcomes under central control (a.k.a. the 'Price of Anarchy'). - Design and analysis of mechanisms that induce truthful behavior or near-optimal outcomes at equilibrium. - Selected current research topics, such as Google's Sponsored Search Auction, the U.S. FCC Spectrum Auction, Kidney Exchange. | |||||||||||
Lecture notes | Lecture notes will be usually posted on the website shortly after each lecture. | |||||||||||
Literature | "Algorithmic Game Theory", edited by N. Nisan, T. Roughgarden, E. Tardos, and V. Vazirani, Cambridge University Press, 2008; "Game Theory and Strategy", Philip D. Straffin, The Mathematical Association of America, 5th printing, 2004 Several copies of both books are available in the Computer Science library. | |||||||||||
Prerequisites / Notice | Audience: Although this is a Computer Science course, we encourage the participation from all students who are interested in this topic. Requirements: You should enjoy precise mathematical reasoning. You need to have passed a course on algorithms and complexity. No knowledge of game theory is required. | |||||||||||
252-1411-00L | Security of Wireless Networks | W | 6 credits | 2V + 1U + 2A | S. Capkun, K. Kostiainen | |||||||
Abstract | Core Elements: Wireless communication channel, Wireless network architectures and protocols, Attacks on wireless networks, Protection techniques. | |||||||||||
Learning objective | After this course, the students should be able to: describe and classify security goals and attacks in wireless networks; describe security architectures of the following wireless systems and networks: 802.11, GSM/UMTS, RFID, ad hoc/sensor networks; reason about security protocols for wireless network; implement mechanisms to secure 802.11 networks. | |||||||||||
Content | Wireless channel basics. Wireless electronic warfare: jamming and target tracking. Basic security protocols in cellular, WLAN and multi-hop networks. Recent advances in security of multi-hop networks; RFID privacy challenges and solutions. | |||||||||||
252-1414-00L | System Security | W | 7 credits | 2V + 2U + 2A | S. Capkun, A. Perrig | |||||||
Abstract | The first part of the lecture covers individual system aspects starting with tamperproof or tamper-resistant hardware in general over operating system related security mechanisms to application software systems, such as host based intrusion detection systems. In the second part, the focus is on system design and methodologies for building secure systems. | |||||||||||
Learning objective | In this lecture, students learn about the security requirements and capabilities that are expected from modern hardware, operating systems, and other software environments. An overview of available technologies, algorithms and standards is given, with which these requirements can be met. | |||||||||||
Content | The first part of the lecture covers individual system's aspects starting with tamperproof or tamperresistant hardware in general over operating system related security mechanisms to application software systems such as host based intrusion detetction systems. The main topics covered are: tamper resistant hardware, CPU support for security, protection mechanisms in the kernel, file system security (permissions / ACLs / network filesystem issues), IPC Security, mechanisms in more modern OS, such as Capabilities and Zones, Libraries and Software tools for security assurance, etc. In the second part, the focus is on system design and methodologies for building secure systems. Topics include: patch management, common software faults (buffer overflows, etc.), writing secure software (design, architecture, QA, testing), compiler-supported security, language-supported security, logging and auditing (BSM audit, dtrace, ...), cryptographic support, and trustworthy computing (TCG, SGX). Along the lectures, model cases will be elaborated and evaluated in the exercises. | |||||||||||
252-1425-00L | Geometry: Combinatorics and Algorithms | W | 8 credits | 3V + 2U + 2A | B. Gärtner, E. Welzl, M. Hoffmann, M. Wettstein | |||||||
Abstract | Geometric structures are useful in many areas, and there is a need to understand their structural properties, and to work with them algorithmically. The lecture addresses theoretical foundations concerning geometric structures. Central objects of interest are triangulations. We study combinatorial (Does a certain object exist?) and algorithmic questions (Can we find a certain object efficiently?) | |||||||||||
Learning objective | The goal is to make students familiar with fundamental concepts, techniques and results in combinatorial and computational geometry, so as to enable them to model, analyze, and solve theoretical and practical problems in the area and in various application domains. In particular, we want to prepare students for conducting independent research, for instance, within the scope of a thesis project. | |||||||||||
Content | Planar and geometric graphs, embeddings and their representation (Whitney's Theorem, canonical orderings, DCEL), polygon triangulations and the art gallery theorem, convexity in R^d, planar convex hull algorithms (Jarvis Wrap, Graham Scan, Chan's Algorithm), point set triangulations, Delaunay triangulations (Lawson flips, lifting map, randomized incremental construction), Voronoi diagrams, the Crossing Lemma and incidence bounds, line arrangements (duality, Zone Theorem, ham-sandwich cuts), 3-SUM hardness, counting planar triangulations. | |||||||||||
Lecture notes | yes | |||||||||||
Literature | Mark de Berg, Marc van Kreveld, Mark Overmars, Otfried Cheong, Computational Geometry: Algorithms and Applications, Springer, 3rd ed., 2008. Satyan Devadoss, Joseph O'Rourke, Discrete and Computational Geometry, Princeton University Press, 2011. Stefan Felsner, Geometric Graphs and Arrangements: Some Chapters from Combinatorial Geometry, Teubner, 2004. Jiri Matousek, Lectures on Discrete Geometry, Springer, 2002. Takao Nishizeki, Md. Saidur Rahman, Planar Graph Drawing, World Scientific, 2004. | |||||||||||
Prerequisites / Notice | Prerequisites: The course assumes basic knowledge of discrete mathematics and algorithms, as supplied in the first semesters of Bachelor Studies at ETH. Outlook: In the following spring semester there is a seminar "Geometry: Combinatorics and Algorithms" that builds on this course. There are ample possibilities for Semester-, Bachelor- and Master Thesis projects in the area. | |||||||||||
252-3005-00L | Natural Language Processing Number of participants limited to 400. | W | 5 credits | 2V + 2U + 1A | R. Cotterell | |||||||
Abstract | This course presents topics in natural language processing with an emphasis on modern techniques, primarily focusing on statistical and deep learning approaches. The course provides an overview of the primary areas of research in language processing as well as a detailed exploration of the models and techniques used both in research and in commercial natural language systems. | |||||||||||
Learning objective | The objective of the course is to learn the basic concepts in the statistical processing of natural languages. The course will be project-oriented so that the students can also gain hands-on experience with state-of-the-art tools and techniques. | |||||||||||
Content | This course presents an introduction to general topics and techniques used in natural language processing today, primarily focusing on statistical approaches. The course provides an overview of the primary areas of research in language processing as well as a detailed exploration of the models and techniques used both in research and in commercial natural language systems. | |||||||||||
Literature | Lectures will make use of textbooks such as the one by Jurafsky and Martin where appropriate, but will also make use of original research and survey papers. | |||||||||||
227-2210-00L | Computer Architecture | W | 8 credits | 6G + 1A | O. Mutlu | |||||||
Abstract | Computer architecture is the science & art of designing and optimizing hardware components and the hardware/software interface to create a computer that meets design goals. This course covers basic components of a modern computing system (memory, processors, interconnects, accelerators). The course takes a hardware/software cooperative approach to understanding and designing computing systems. | |||||||||||
Learning objective | We will learn the fundamental concepts of the different parts of modern computing systems, as well as the latest major research topics in Industry and Academia. We will extensively cover memory systems (including DRAM and new Non-Volatile Memory technologies, memory controllers, flash memory), parallel computing systems (including multicore processors, coherence and consistency, GPUs), heterogeneous computing, processing-in-memory, interconnection networks, specialized systems for major data-intensive workloads (e.g. graph analytics, bioinformatics, machine learning), etc. | |||||||||||
Content | The principles presented in the lecture are reinforced in the laboratory through 1) the design and implementation of a cycle-accurate simulator, where we will explore different components of a modern computing system (e.g., pipeline, memory hierarchy, branch prediction, prefetching, caches, multithreading), and 2) the extension of state-of-the-art research simulators (e.g., Ramulator) for more in-depth understanding of specific system components (e.g., memory scheduling, prefetching). | |||||||||||
Lecture notes | All the materials (including lecture slides) will be provided on the course website: https://safari.ethz.ch/architecture/ The video recordings of the lectures are expected to be made available after lectures. | |||||||||||
Literature | We will provide required and recommended readings in every lecture. They will mainly consist of research papers presented in major Computer Architecture and related conferences and journals. | |||||||||||
Prerequisites / Notice | Digital Design and Computer Architecture. | |||||||||||
263-2400-00L | Reliable and Trustworthy Artificial Intelligence | W | 6 credits | 2V + 2U + 1A | M. Vechev | |||||||
Abstract | Creating reliable and explainable probabilistic models is a fundamental challenge to solving the artificial intelligence problem. This course covers some of the latest and most exciting advances that bring us closer to constructing such models. | |||||||||||
Learning objective | The 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. To facilitate deeper understanding, an important part of the course will be a group hands-on programming project where students will build a system based on the learned material. | |||||||||||
Content | This comprehensive course covers some of the latest and most important research advances (over the last 3 years) underlying the creation of safe, trustworthy, and reliable AI (more information here: https://www.sri.inf.ethz.ch/teaching/reliableai21): * Adversarial Attacks on Deep Learning (noise-based, geometry attacks, sound attacks, physical attacks, autonomous driving, out-of-distribution) * Defenses against attacks * Combining gradient-based optimization with logic for encoding background knowledge * Complete Certification of deep neural networks via automated reasoning (e.g., via numerical relaxations, mixed-integer solvers). * Probabilistic certification of deep neural networks * Training deep neural networks to be provably robust via automated reasoning * Fairness (different notions of fairness, certifiably fair representation learning) * Federated Learning (introduction, security considerations) | |||||||||||
Prerequisites / Notice | While not a formal requirement, the course assumes familiarity with basics of machine learning (especially linear algebra, gradient descent, and neural networks as well as basic probability theory). These topics are usually covered in “Intro to ML” classes at most institutions (e.g., “Introduction to Machine Learning” at ETH). For solving assignments, some programming experience in Python is expected. | |||||||||||
263-2800-00L | Design of Parallel and High-Performance Computing Number of participants limited to 125. | W | 9 credits | 3V + 2U + 3A | T. Hoefler, M. Püschel | |||||||
Abstract | Advanced topics in parallel and high-performance computing. | |||||||||||
Learning objective | Understand concurrency paradigms and models from a higher perspective and acquire skills for designing, structuring and developing possibly large parallel high-performance software systems. Become able to distinguish parallelism in problem space and in machine space. Become familiar with important technical concepts and with concurrency folklore. | |||||||||||
Content | We will cover all aspects of high-performance computing ranging from architecture through programming up to algorithms. We will start with a discussion of caches and cache coherence in practical computer systems. We will dive into parallel programming concepts such as memory models, locks, and lock-free. We will cover performance modeling and parallel design principles as well as basic parallel algorithms. | |||||||||||
Prerequisites / Notice | This class is intended for the Computer Science Masters curriculum. Students must have basic knowledge in programming in C as well as computer science theory. Students should be familiar with the material covered in the ETH computer science first-year courses "Parallele Programmierung (parallel programming)" and "Algorithmen und Datenstrukturen (algorithm and data structures)" or equivalent courses. | |||||||||||
263-3010-00L | Big Data | W | 10 credits | 3V + 2U + 4A | G. Fourny | |||||||
Abstract | The key challenge of the information society is to turn data into information, information into knowledge, knowledge into value. This has become increasingly complex. Data comes in larger volumes, diverse shapes, from different sources. Data is more heterogeneous and less structured than forty years ago. Nevertheless, it still needs to be processed fast, with support for complex operations. | |||||||||||
Learning objective | This combination of requirements, together with the technologies that have emerged in order to address them, is typically referred to as "Big Data." This revolution has led to a completely new way to do business, e.g., develop new products and business models, but also to do science -- which is sometimes referred to as data-driven science or the "fourth paradigm". Unfortunately, the quantity of data produced and available -- now in the Zettabyte range (that's 21 zeros) per year -- keeps growing faster than our ability to process it. Hence, new architectures and approaches for processing it were and are still needed. Harnessing them must involve a deep understanding of data not only in the large, but also in the small. The field of databases evolves at a fast pace. In order to be prepared, to the extent possible, to the (r)evolutions that will take place in the next few decades, the emphasis of the lecture will be on the paradigms and core design ideas, while today's technologies will serve as supporting illustrations thereof. After visiting this lecture, you should have gained an overview and understanding of the Big Data landscape, which is the basis on which one can make informed decisions, i.e., pick and orchestrate the relevant technologies together for addressing each business use case efficiently and consistently. | |||||||||||
Content | This course gives an overview of database technologies and of the most important database design principles that lay the foundations of the Big Data universe. We take the monolithic, one-machine relational stack from the 1970s, smash it down and rebuild it on top of large clusters: starting with distributed storage, and all the way up to syntax, models, validation, processing, indexing, and querying. A broad range of aspects is covered with a focus on how they fit all together in the big picture of the Big Data ecosystem. No data is harmed during this course, however, please be psychologically prepared that our data may not always be in third normal form. - physical storage: distributed file systems (HDFS), object storage(S3), key-value stores - logical storage: document stores (MongoDB), column stores (HBase), graph databases (neo4j), data warehouses (ROLAP) - data formats and syntaxes (XML, JSON, RDF, Turtle, CSV, XBRL, YAML, protocol buffers, Avro) - data shapes and models (tables, trees, graphs, cubes) - type systems and schemas: atomic types, structured types (arrays, maps), set-based type systems (?, *, +) - an overview of functional, declarative programming languages across data shapes (SQL, XQuery, JSONiq, Cypher, MDX) - the most important query paradigms (selection, projection, joining, grouping, ordering, windowing) - paradigms for parallel processing, two-stage (MapReduce) and DAG-based (Spark) - resource management (YARN) - what a data center is made of and why it matters (racks, nodes, ...) - underlying architectures (internal machinery of HDFS, HBase, Spark, neo4j) - optimization techniques (functional and declarative paradigms, query plans, rewrites, indexing) - applications. Large scale analytics and machine learning are outside of the scope of this course. | |||||||||||
Literature | Papers from scientific conferences and journals. References will be given as part of the course material during the semester. | |||||||||||
Prerequisites / Notice | This course, in the autumn semester, is only intended for: - Computer Science students - Data Science students - CBB students with a Computer Science background Mobility students in CS are also welcome and encouraged to attend. If you experience any issue while registering, please contact the study administration and you will be gladly added. For students of all other departements interested in this fascinating topic: I would love to have you visit my lectures as well! So there is a series of two courses specially designed for you: - "Information Systems for Engineers" (SQL, relational databases): this Fall - "Big Data for Engineers" (similar to Big Data, but adapted for non Computer Scientists): Spring 2021 There is no hard dependency, so you can either them in any order, but it may be more enjoyable to start with Information Systems for Engineers. Students who successfully completed Big Data for Engineers are not allowed to enrol in the course Big Data. | |||||||||||
263-3210-00L | Deep Learning Number of participants limited to 320. | W | 8 credits | 3V + 2U + 2A | F. Perez Cruz, A. Lucchi | |||||||
Abstract | Deep learning is an area within machine learning that deals with algorithms and models that automatically induce multi-level data representations. | |||||||||||
Learning objective | In recent years, deep learning and deep networks have significantly improved the state-of-the-art in many application domains such as computer vision, speech recognition, and natural language processing. This class will cover the mathematical foundations of deep learning and provide insights into model design, training, and validation. The main objective is a profound understanding of why these methods work and how. There will also be a rich set of hands-on tasks and practical projects to familiarize students with this emerging technology. | |||||||||||
Prerequisites / Notice | This is an advanced level course that requires some basic background in machine learning. More importantly, students are expected to have a very solid mathematical foundation, including linear algebra, multivariate calculus, and probability. The course will make heavy use of mathematics and is not (!) meant to be an extended tutorial of how to train deep networks with tools like Torch or Tensorflow, although that may be a side benefit. The participation in the course is subject to the following condition: - Students must have taken the exam in Advanced Machine Learning (252-0535-00) or have acquired equivalent knowledge, see exhaustive list below: Advanced Machine Learning https://ml2.inf.ethz.ch/courses/aml/ Computational Intelligence Lab http://da.inf.ethz.ch/teaching/2019/CIL/ Introduction to Machine Learning https://las.inf.ethz.ch/teaching/introml-S19 Statistical Learning Theory http://ml2.inf.ethz.ch/courses/slt/ Computational Statistics https://stat.ethz.ch/lectures/ss19/comp-stats.php Probabilistic Artificial Intelligence https://las.inf.ethz.ch/teaching/pai-f18 | |||||||||||
263-3845-00L | Data Management Systems | W | 8 credits | 3V + 1U + 3A | G. Alonso | |||||||
Abstract | The course will cover the implementation aspects of data management systems using relational database engines as a starting point to cover the basic concepts of efficient data processing and then expanding those concepts to modern implementations in data centers and the cloud. | |||||||||||
Learning objective | The goal of the course is to convey the fundamental aspects of efficient data management from a systems implementation perspective: storage, access, organization, indexing, consistency, concurrency, transactions, distribution, query compilation vs interpretation, data representations, etc. Using conventional relational engines as a starting point, the course will aim at providing an in depth coverage of the latest technologies used in data centers and the cloud to implement large scale data processing in various forms. | |||||||||||
Content | The course will first cover fundamental concepts in data management: storage, locality, query optimization, declarative interfaces, concurrency control and recovery, buffer managers, management of the memory hierarchy, presenting them in a system independent manner. The course will place an special emphasis on understating these basic principles as they are key to understanding what problems existing systems try to address. It will then proceed to explore their implementation in modern relational engines supporting SQL to then expand the range of systems used in the cloud: key value stores, geo-replication, query as a service, serverless, large scale analytics engines, etc. | |||||||||||
Literature | The main source of information for the course will be articles and research papers describing the architecture of the systems discussed. The list of papers will be provided at the beginning of the course. | |||||||||||
Prerequisites / Notice | The course requires to have completed the Data Modeling and Data Bases course at the Bachelor level as it assumes knowledge of databases and SQL. | |||||||||||
Competencies |
| |||||||||||
263-3850-00L | Informal Methods | W | 5 credits | 2G + 2A | D. Cock | |||||||
Abstract | Formal methods are increasingly a key part of the methodological toolkit of systems programmers - those writing operating systems, databases, and distributed systems. This course is about how to apply concepts, techniques, and principles from formal methods to such software systems, and how to get into the habit of thinking formally about systems design even when writing low-level C code. | |||||||||||
Learning objective | This course is about equipping students whose focus is systems with the insights and conceptual tools provided by formal methods, and thereby enabling them to become better systems programmers. By the end of the course, students should be able to seamlessly integrate basic concepts form formal methods into how they conceive, design, implement, reason about, and debug computer systems. The goal is not to provide a comprehensive introduction to formal methods - this is well covered by other courses in the department. Instead, it is intended to provide students in computer systems (who may or may not have existing background knowledge of formal methods) with a basis for applying formal methods in their work. | |||||||||||
Content | This course does not assume prior knowledge of formal methods, and will start with a quick review of topics such static vs. dynamic reasoning, variants and invariants, program algebra and refinement, etc. However, it is strongly recommended that students have already taken one of the introductory formal methods course at ETH (or equivalents elsewhere) before taking this course - the emphasis is on reinforcing these concepts by applying them, not to teach them from scratch. Instead, the majority of the course will be about how to apply these techniques to actual, practical code in real systems. We will work from real systems code written both by students taking the course, and practical systems developed using formal techniques, in particular the verified seL4 microkernel will be a key case study. We will also focus on informal, pen-and-paper arguments for correctness of programs and systems rather than using theorem provers or automated verification tools; again these latter techniques are well covered in other courses (and recommended as a complement to this one). | |||||||||||
263-4500-00L | Advanced Algorithms Takes place for the last time. | W | 9 credits | 3V + 2U + 3A | M. Ghaffari, G. Zuzic | |||||||
Abstract | This is a graduate-level course on algorithm design (and analysis). It covers a range of topics and techniques in approximation algorithms, sketching and streaming algorithms, and online algorithms. | |||||||||||
Learning objective | This course familiarizes the students with some of the main tools and techniques in modern subareas of algorithm design. | |||||||||||
Content | The lectures will cover a range of topics, tentatively including the following: graph sparsifications while preserving cuts or distances, various approximation algorithms techniques and concepts, metric embeddings and probabilistic tree embeddings, online algorithms, multiplicative weight updates, streaming algorithms, sketching algorithms, and derandomization. | |||||||||||
Lecture notes | https://people.inf.ethz.ch/gmohsen/AA21/ | |||||||||||
Prerequisites / Notice | This course is designed for masters and doctoral students and it especially targets those interested in theoretical computer science, but it should also be accessible to last-year bachelor students. Sufficient comfort with both (A) Algorithm Design & Analysis and (B) Probability & Concentrations. E.g., having passed the course Algorithms, Probability, and Computing (APC) is highly recommended, though not required formally. If you are not sure whether you're ready for this class or not, please consult the instructor. |
- Page 1 of 2 All