Marloes H. Maathuis: Katalogdaten im Frühjahrssemester 2019 |
Name | Frau Prof. Dr. Marloes H. Maathuis |
Lehrgebiet | Statistik |
Adresse | Seminar für Statistik (SfS) ETH Zürich, HG G 24.1 Rämistrasse 101 8092 Zürich SWITZERLAND |
Telefon | +41 44 632 61 84 |
URL | http://stat.ethz.ch/~maathuis |
Departement | Mathematik |
Beziehung | Ordentliche Professorin |
Nummer | Titel | ECTS | Umfang | Dozierende | |
---|---|---|---|---|---|
401-3620-19L | Student Seminar in Statistics: Adversarial and Robust Machine Learning Maximale Teilnehmerzahl: 22 Hauptsächlich für Studierende der Bachelor- und Master-Studiengänge Mathematik, welche nach der einführenden Lerneinheit 401-2604-00L Wahrscheinlichkeit und Statistik (Probability and Statistics) mindestens ein Kernfach oder Wahlfach in Statistik besucht haben. Das Seminar wird auch für Studierende der Master-Studiengänge Statistik bzw. Data Science angeboten. | 4 KP | 2S | P. L. Bühlmann, M. H. Maathuis, N. Meinshausen, S. van de Geer | |
Kurzbeschreibung | As statistical and machine learning models are increasingly employed in many real-world applications it becomes more important to understand the vulnerabilities and robustness properties of these models. In the first part of this seminar, we will study papers relating to adversarial examples. In the second part of the course, we will review other types of distribution shifts. | ||||
Lernziel | After this seminar, you should know - properties of adversarial examples - some attacks and defenses - some concepts from robust optimization and distributional robustness - other distribution shifts that can fool machine learning models in general and neural networks in particular | ||||
Inhalt | As statistical and machine learning models are increasingly employed in many real-world applications it becomes more important to understand the vulnerabilities and robustness properties of these models. In the first part of this seminar, we will study papers relating to adversarial examples, covering their properties, various attacks and defenses. In the second part of the course, we will review other types of distribution shifts, posing significant challenges for state-of-the-art machine learning models. Some parts of the seminar will be devoted to implementing these methods in python. | ||||
Voraussetzungen / Besonderes | We require at least one course in statistics or machine learning and basic knowledge in computer programming. Some background knowledge in deep learning is helpful but not strictly required. Topics will be assigned during the first meeting. | ||||
401-3632-00L | Computational Statistics | 8 KP | 3V + 1U | M. H. Maathuis | |
Kurzbeschreibung | We discuss modern statistical methods for data analysis, including methods for data exploration, prediction and inference. We pay attention to algorithmic aspects, theoretical properties and practical considerations. The class is hands-on and methods are applied using the statistical programming language R. | ||||
Lernziel | The student obtains an overview of modern statistical methods for data analysis, including their algorithmic aspects and theoretical properties. The methods are applied using the statistical programming language R. | ||||
Voraussetzungen / Besonderes | At least one semester of (basic) probability and statistics. Programming experience is helpful but not required. | ||||
401-4620-00L | Statistics Lab Maximale Teilnehmerzahl: 27 | 6 KP | 2S | M. Kalisch, M. H. Maathuis, M. Mächler, L. Meier, N. Meinshausen | |
Kurzbeschreibung | "Statistics Lab" is an Applied Statistics Workshop in Data Analysis. It provides a learning environment in a realistic setting. Students lead a regular consulting session at the Seminar für Statistik (SfS). After the session, the statistical data analysis is carried out and a written report and results are presented to the client. The project is also presented in the course's seminar. | ||||
Lernziel | - gain initial experience in the consultancy process - carry out a consultancy session and produce a report - apply theoretical knowledge to an applied problem After the course, students will have practical knowledge about statistical consulting. They will have determined the scientific problem and its context, enquired the design of the experiment or data collection, and selected the appropriate methods to tackle the problem. They will have deepened their statistical knowledge, and applied their theoretical knowledge to the problem. They will have gathered experience in explaining the relevant mathematical and software issues to a client. They will have performed a statistical analysis using R (or SPSS). They improve their skills in writing a report and presenting statistical issues in a talk. | ||||
Inhalt | Students participate in consulting meetings at the SfS. Several consulting dates are available for student participation. These are arranged individually. -During the first meeting the student mainly observes and participates in the discussion. During the second meeting (with a different client), the student leads the meeting. The member of the consulting team is overseeing (and contributing to) the meeting. -After the meeting, the student performs the recommended analysis, produces a report and presents the results to the client. -Finally, the student presents the case in the weekly course seminar in a talk. All students are required to attend the seminar regularly. | ||||
Skript | n/a | ||||
Literatur | The required literature will depend on the specific statistical problem under investigation. Some introductory material can be found below. | ||||
Voraussetzungen / Besonderes | Prerequisites: Sound knowledge in basic statistical methods, especially regression and, if possible, analysis of variance. Basic experience in Data Analysis with R. | ||||
401-5620-00L | Research Seminar on Statistics | 0 KP | 2K | P. L. Bühlmann, L. Held, T. Hothorn, D. Kozbur, M. H. Maathuis, N. Meinshausen, S. van de Geer, M. Wolf | |
Kurzbeschreibung | Forschungskolloquium | ||||
Lernziel | |||||
401-5640-00L | ZüKoSt: Seminar on Applied Statistics | 0 KP | 1K | M. Kalisch, P. L. Bühlmann, R. Furrer, L. Held, T. Hothorn, M. H. Maathuis, M. Mächler, L. Meier, N. Meinshausen, M. Robinson, C. Strobl, S. van de Geer | |
Kurzbeschreibung | 5 bis 6 Vorträge zur angewandten Statistik. | ||||
Lernziel | Kennenlernen von statistischen Methoden in ihrer Anwendung in verschiedenen Gebieten, besonders in Naturwissenschaft, Technik und Medizin. | ||||
Inhalt | In 5-6 Einzelvorträgen pro Semester werden Methoden der Statistik einzeln oder überblicksartig vorgestellt, oder es werden Probleme und Problemtypen aus einzelnen Anwendungsgebieten besprochen. 3 bis 4 der Vorträge stehen in der Regel unter einem Semesterthema. | ||||
Skript | Bei manchen Vorträgen werden Unterlagen verteilt. Eine Zusammenfassung ist kurz vor den Vorträgen im Internet unter http://stat.ethz.ch/talks/zukost abrufbar. Ankündigunen der Vorträge werden auf Wunsch zugesandt. | ||||
Voraussetzungen / Besonderes | Dies ist keine Vorlesung. Es wird keine Prüfung durchgeführt, und es werden keine Kreditpunkte vergeben. Nach besonderem Programm. Koordinator M. Kalisch, Tel. 044 632 3435 Lehrsprache ist Englisch oder Deutsch je nach ReferentIn. Course language is English or German and may depend on the speaker. | ||||
401-5680-00L | Foundations of Data Science Seminar | 0 KP | P. L. Bühlmann, H. Bölcskei, J. M. Buhmann, T. Hofmann, A. Krause, A. Lapidoth, H.‑A. Loeliger, M. H. Maathuis, N. Meinshausen, G. Rätsch, S. van de Geer | ||
Kurzbeschreibung | Research colloquium | ||||
Lernziel |