Andreas Krause: Catalogue data in Autumn Semester 2017
|Name||Prof. Dr. Andreas Krause|
Institut für Maschinelles Lernen
ETH Zürich, CAB G 81.2
|Telephone||+41 44 632 63 22|
|Fax||+41 44 623 15 62|
|252-0945-05L||Doctoral Seminar Machine Learning (HS17) |
Only for Computer Science Ph.D. students.
|1 credit||2S||J. M. Buhmann, T. Hofmann, A. Krause, G. Rätsch|
|Abstract||An essential aspect of any research project is dissemination of the findings arising from the study. Here we focus on oral communication, which includes: appropriate selection of material, preparation of the visual aids (slides and/or posters), and presentation skills.|
|Objective||The seminar participants should learn how to prepare and deliver scientific talks as well as to deal with technical questions. Participants are also expected to actively contribute to discussions during presentations by others, thus learning and practicing critical thinking skills.|
|Prerequisites / Notice||This doctoral seminar of the Machine Learning Laboratory of ETH is intended for PhD students who work on a machine learning project, i.e., for the PhD students of the ML lab.|
|252-5051-00L||Advanced Topics in Machine Learning |
Number of participants limited to 40.
|2 credits||2S||J. M. Buhmann, T. Hofmann, A. Krause, G. Rätsch|
|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.|
|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.|
|263-5200-00L||Data Mining: Learning from Large Data Sets||4 credits||2V + 1U||A. Krause, Y. Levy|
|Abstract||Many scientific and commercial applications require insights from massive, high-dimensional data sets. This courses introduces principled, state-of-the-art techniques from statistics, algorithms and discrete and convex optimization for learning from such large data sets. The course both covers theoretical foundations and practical applications.|
|Objective||Many scientific and commercial applications require us to obtain insights from massive, high-dimensional data sets. In this graduate-level course, we will study principled, state-of-the-art techniques from statistics, algorithms and discrete and convex optimization for learning from such large data sets. The course will both cover theoretical foundations and practical applications.|
- Dealing with large data (Data centers; Map-Reduce/Hadoop; Amazon Mechanical Turk)
- Fast nearest neighbor methods (Shingling, locality sensitive hashing)
- Online learning (Online optimization and regret minimization, online convex programming, applications to large-scale Support Vector Machines)
- Multi-armed bandits (exploration-exploitation tradeoffs, applications to online advertising and relevance feedback)
- Active learning (uncertainty sampling, pool-based methods, label complexity)
- Dimension reduction (random projections, nonlinear methods)
- Data streams (Sketches, coresets, applications to online clustering)
- Recommender systems
|Prerequisites / Notice||Prerequisites: Solid basic knowledge in statistics, algorithms and programming. Background in machine learning is helpful but not required.|
|263-5210-00L||Probabilistic Artificial Intelligence||4 credits||2V + 1U||A. Krause|
|Abstract||This course introduces core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as sensor networks, robotics, and the Internet.|
|Objective||How can we build systems that perform well in uncertain environments and unforeseen situations? How can we develop systems that exhibit "intelligent" behavior, without prescribing explicit rules? How can we build systems that learn from experience in order to improve their performance? We will study core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as sensor networks, robotics, and the Internet. The course is designed for upper-level undergraduate and graduate students.|
- Search (BFS, DFS, A*), constraint satisfaction and optimization
- Tutorial in logic (propositional, first-order)
- Bayesian Networks (models, exact and approximative inference, learning) - Temporal models (Hidden Markov Models, Dynamic Bayesian Networks)
- Probabilistic palnning (MDPs, POMPDPs)
- Reinforcement learning
- Combining logic and probability
|Prerequisites / Notice||Solid basic knowledge in statistics, algorithms and programming|
|701-0901-00L||ETH Week 2017: Manufacturing the Future |
All ETH Bachelor¿s, Master¿s and exchange students can take part in the ETH week. No prior knowledge is required
|1 credit||3S||R. Knutti, C. Bratrich, S. Brusoni, I. Burgert, A. Cabello Llamas, F. Gramazio, G. Grote, A. Krause, M. Meboldt, A. R. Studart, A. Vaterlaus|
|Abstract||The ETH Week is an innovative one-week course designed to foster critical thinking and creative learning. Students from all departments as well as professors and external experts will work together in interdisciplinary teams. They will develop interventions that could play a role in solving some of our most pressing global challenges. In 2017, ETH Week will focus on the topic of manufacturing.|
|Objective||- Domain specific knowledge: Students have immersed knowledge about a certain complex, societal topic which will be selected every year. They understand the complex system context of the current topic, by comprehending its scientific, technical, political, social, ecological and economic perspectives.|
- Analytical skills: The ETH Week participants are able to structure complex problems systematically using selected methods. They are able to acquire further knowledge and to critically analyze the knowledge in interdisciplinary groups and with experts and the help of team tutors.
- Design skills: The students are able to use their knowledge and skills to develop concrete approaches for problem solving and decision making to a selected problem statement, critically reflect these approaches, assess their feasibility, to transfer them into a concrete form (physical model, prototypes, strategy paper, etc.) and to present this work in a creative way (role-plays, videos, exhibitions, etc.).
- Self-competence: The students are able to plan their work effectively, efficiently and autonomously. By considering approaches from different disciplines they are able to make a judgment and form a personal opinion. In exchange with non-academic partners from business, politics, administration, nongovernmental organizations and media they are able to communicate appropriately, present their results professionally and creatively and convince a critical audience.
- Social competence: The students are able to work in multidisciplinary teams, i.e. they can reflect critically their own discipline, debate with students from other disciplines and experts in a critical-constructive and respectful way and can relate their own positions to different intellectual approaches. They can assess how far they are able to actively make a contribution to society by using their personal and professional talents and skills and as "Change Agents".
|Content||The week is mainly about problem solving and design thinking applied to the complex manufacturing world. During ETH Week students will have the opportunity to work in small interdisciplinary groups, allowing them to critically analyze both their own approaches and those of other disciplines, and to integrate these into their work. |
While deepening their knowledge about how manufacturing works, students will be introduced to various methods and tools for generating creative ideas and understand how different people are affected by each part of the system. In addition to lectures and literature, students will acquire knowledge via excursions into the real world, empirical observations, and conversations with researchers and experts.
A key attribute of the ETH Week is that students are expected to find their own problem, rather than just solve the problem that has been handed to them.
Therefore, the first three days of the week will concentrate on identifying a problem the individual teams will work on, while the last two days are focused on generating solutions and communicating the team's ideas.
|Prerequisites / Notice||No prerequisites. Program is open to Bachelor and Masters from all ETH Departments. All students must apply through a competitive application process at www.ethz.ch/ethweek. Participation is subject to successful selection through this competitive process.|