Search result: Catalogue data in Spring Semester 2020

Computer Science Master Information
Focus Courses
Focus Courses General Studies
Seminar in General Studies
NumberTitleTypeECTSHoursLecturers
263-2926-00LDeep Learning for Big Code Information Restricted registration - show details
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.
W2 credits2SV. Raychev
AbstractThe seminar covers some of the latest and most exciting developments (industrial and research) in the field of Deep Learning for Code, including new methods and latest systems, as well as open challenges and opportunities.
ObjectiveThe objective of the seminar is to:

- Introduce students to the field of Deep Learning for Big Code.

- Learn how machine learning models can be used to solve practical challenges in software engineering and programming beyond traditional methods.

- Highlight the latest research and work opportunities in industry and academia available on this topic.
ContentThe last 5 years have seen increased interest in applying advanced machine learning techniques such as deep learning to new kind of data: program code. As the size of open source code increases dramatically (over 980 billion lines of code written by humans), so comes the opportunity for new kind of deep probabilistic methods and commercial systems that leverage this data to revolutionize software creation and address hard problems not previously possible. Examples include: machines writing code, program de-obfuscation for security, code search, and many more.

Interestingly, this new type of data, unlike natural language and images, introduces technical challenges not typically encountered when working with standard datasets (e.g., images, videos, natural language), for instance, finding the right representation over which deep learning operates. This in turn has the potential to drive new kinds of machine learning models with broad applicability.

Because of this, there has been substantial interest over the last few years in both industry (e.g., companies such as Facebook starting, various start-ups in the space such as http://deepcode.ai), academia (e.g., http://plml.ethz.ch) and government agencies (e.g., DARPA) on using machine learning to automate various programming tasks.

In this seminar, we will cover some of the latest and most exciting developments in the field of Deep Learning for Code, including new methods and latest systems, as well as open challenges and opportunities.

The seminar is carried out as a set of presentations chosen from a list of available papers. The grade is determined as a function of the presentation, handling questions and answers, and participation.
Prerequisites / NoticeThe seminar is carried out as a set of presentations chosen from a list of available papers. The grade is determined as a function of the presentation, handling questions and answers, and participation.

The seminar is ideally suited for M.Sc. students in Computer Science.
263-3840-00LHardware Architectures for Machine Learning Information
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.
W2 credits2SG. Alonso, T. Hoefler, C. Zhang
AbstractThe seminar covers recent results in the increasingly important field of hardware acceleration for data science and machine learning, both in dedicated machines or in data centers.
ObjectiveThe seminar aims at students interested in the system aspects of machine learning, who are willing to bridge the gap across traditional disciplines: machine learning, databases, systems, and computer architecture.
ContentThe seminar is intended to cover recent results in the increasingly important field of hardware acceleration for data science and machine learning, both in dedicated machines or in data centers.
Prerequisites / NoticeThe seminar should be of special interest to students intending to complete a master's thesis or a doctoral dissertation in related topics.
263-4651-00LCurrent Topics in Cryptography Information Restricted registration - show details
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.
W2 credits2SD. Hofheinz, U. Maurer, K. Paterson
AbstractIn this seminar course, students present and discuss a variety of recent research papers in Cryptography.
ObjectiveIndependent study of scientific literature and assessment of its contributions as well as learning and practicing presentation techniques.
ContentThe course lecturers will provide a list of papers from which students will select.
LiteratureThe reading list will be published on the course website.
Prerequisites / NoticeIdeally, students will have taken the D-INFK Bachelors course “Information Security" or an equivalent course at Bachelors level. Ideally, they will have attended or will attend in parallel the Masters course in "Applied Cryptography”.
263-5225-00LAdvanced Topics in Machine Learning and Data Science Restricted registration - show details
Number of participants limited to 20.

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.
W2 credits2SF. Perez Cruz
AbstractIn this seminar, recent papers of the machine learning and data science literature are presented and discussed. Possible topics cover statistical models, machine learning algorithms and its applications.
ObjectiveThe seminar “Advanced Topics in Machine Learning and Data Science” familiarizes students with recent developments in machine learning and data science. Recently published articles, as well as influential papers, have to be presented and critically reviewed. The students will learn how to structure a scientific presentation, which covers the motivation, key ideas and main results of a scientific paper. An important goal of the seminar presentation is to summarize the essential ideas of the paper in sufficient depth for the audience to be able to follow its main conclusion, especially why the article is (or is not) worth attention. The presentation style will play an important role and should reach the level of professional scientific presentations.
ContentThe seminar will cover a number of recent papers which have emerged as important contributions to the machine learning and data science literatures. The topics will vary from year to year but they are centered on methodological issues in machine learning and its application, not only to text or images, but other scientific
domains like medicine, climate or physics.
LiteratureThe papers will be presented in the first session of the seminar.
263-5904-00LDeep Learning for Computer Vision: Seminal Work Information Restricted registration - show details
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.
W2 credits2SM. R. Oswald, Z. Cui
AbstractThis seminar covers seminal papers on the topic of deep learning for computer vision. The students will present and discuss the papers and gain an understanding of the most influential research in this area - both past and present.
ObjectiveThe objectives of this seminar are two-fold. Firstly, the aim is to provide a solid understanding of key contributions to the field of deep learning for vision (including a historical perspective as well as recent work). Secondly, the students will learn to critically read and analyse original research papers and judge their impact, as well as how to give a scientific presentation and lead a discussion on their topic.
ContentThe seminar will start with introductory lectures to provide (1) a compact overview of challenges and relevant machine learning and deep learning research, and (2) a tutorial on critical analysis and presentation of research papers. Each student then chooses one paper from the provided collection to present during the remainder of the seminar. The students will be supported in the preparation of their presentation by the seminar assistants.
Lecture notesThe selection of research papers will be presented at the beginning of the semester.
LiteratureThe course "Machine Learning" is recommended.
227-0559-00LSeminar in Deep Reinforcement Learning Information Restricted registration - show details
Number of participants limited to 25.
W2 credits2SR. Wattenhofer, O. Richter
AbstractIn this seminar participating students present and discuss recent research papers in the area of deep reinforcement learning. The seminar starts with two introductory lessons introducing the basic concepts. Alongside the seminar a programming challenge is posed in which students can take part to improve their grade.
ObjectiveSince Google Deepmind presented the Deep Q-Network (DQN) algorithm in 2015 that could play Atari-2600 games at a superhuman level, the field of deep reinforcement learning gained a lot of traction. It sparked media attention with AlphaGo and AlphaZero and is one of the most prominent research areas. Yet many research papers in the area come from one of two sources: Google Deepmind or OpenAI. In this seminar we aim at giving the students an in depth view on the current advances in the area by discussing recent papers as well as discussing current issues and difficulties surrounding deep reinforcement learning.
ContentTwo introductory courses introducing Q-learning and policy gradient methods. Afterwards participating students present recent papers. For details see: www.disco.ethz.ch/courses.html
Lecture notesSlides of presentations will be made available.
LiteratureOpenAI course (https://spinningup.openai.com/en/latest/) plus selected papers.
The paper selection can be found on www.disco.ethz.ch/courses.html.
Prerequisites / NoticeIt is expected that student have prior knowledge and interest in machine and deep learning, for instance by having attended appropriate courses.
227-0559-10LSeminar in Communication Networks: Learning, Reasoning and Control Restricted registration - show details
Does not take place this semester.
Number of participants limited to 24.
W2 credits2SL. Vanbever, A. Singla
AbstractIn this seminar participating students review, present, and discuss (mostly recent) research papers in the area of computer networks. This semester the seminar will focus on topics blending networks with machine learning and control theory.
ObjectiveThe two main goals of this seminar are: 1) learning how to read and review scientific papers; and 2) learning how to present and discuss technical topics with an audience of peers.

Students are required to attend the entire seminar, choose a paper to present from a given list, prepare and give a presentation on that topic, and lead the follow-up discussion. To ensure the talks' quality, each student will be mentored by a teaching assistant. In addition to presenting one paper, every student is also required to submit one (short) review for one of the two papers presented every week in-class (12 reviews in total).

The students will be evaluated based on their submitted reviews, their presentation, their leadership in animating the discussion for their own paper, and their participation in the discussions of other papers.
ContentThe seminar will start with two introductory lectures in week 1 and week 2. Starting from week 3, participating students will start reviewing, presenting, and discussing research papers. Each week will see two presentations, for a total of 24 papers.

The course content will vary from semester to semester. This semester, the seminar will focus on topics blending networks with machine learning and control theory. For details, please see: https://seminar-net.ethz.ch
Lecture notesThe slides of each presentation will be made available on the website.
LiteratureThe paper selection will be made available on the course website: https://seminar-net.ethz.ch
Prerequisites / NoticeCommunication Networks (227-0120-00L) or equivalents. It is expected that students have prior knowledge in machine learning and control theory, for instance by having attended appropriate courses.
227-0126-00LAdvanced Topics in Networked Embedded SystemsW2 credits1SL. Thiele, J. Beutel
AbstractThe seminar will cover advanced topics in networked embedded systems. A particular focus are cyber-physical systems, internet of things, and sensor networks in various application domains.
ObjectiveThe goal is to get a deeper understanding on leading edge technologies in the discipline, on classes of applications, and on current as well as future research directions. In addition, participants will improve their presentation, reading and reviewing skills.
ContentThe seminar enables Master students, PhDs and Postdocs to learn about latest breakthroughs in wireless sensor networks, networked embedded systems and devices, and energy-harvesting in several application domains, including environmental monitoring, tracking, smart buildings and control. Participants are requested to actively participate in the organization and preparation of the seminar. In particular, they review all presented papers using a standard scientific reviewing system, they present one of the papers orally and they lead the corresponding discussion session.
851-0740-00LBig Data, Law, and Policy Restricted registration - show details
Number of participants limited to 35

Students will be informed by 1.3.2020 at the latest.
W3 credits2SS. Bechtold
AbstractThis course introduces students to societal perspectives on the big data revolution. Discussing important contributions from machine learning and data science, the course explores their legal, economic, ethical, and political implications in the past, present, and future.
ObjectiveThis course is intended both for students of machine learning and data science who want to reflect on the societal implications of their field, and for students from other disciplines who want to explore the societal impact of data sciences. The course will first discuss some of the methodological foundations of machine learning, followed by a discussion of research papers and real-world applications where big data and societal values may clash. Potential topics include the implications of big data for privacy, liability, insurance, health systems, voting, and democratic institutions, as well as the use of predictive algorithms for price discrimination and the criminal justice system. Guest speakers, weekly readings and reaction papers ensure a lively debate among participants from various backgrounds.
  • First page Previous page Page  3  of  3     All