Gunnar Rätsch: Catalogue data in Autumn Semester 2023

Name Prof. Dr. Gunnar Rätsch
FieldBiomedical
Address
Professur für Biomedizininformatik
ETH Zürich, CAB F 53.2
Universitätstrasse 6
8092 Zürich
SWITZERLAND
Telephone+41 44 632 20 36
E-mailraetsch@inf.ethz.ch
URLhttp://bmi.inf.ethz.ch
DepartmentComputer Science
RelationshipFull Professor

NumberTitleECTSHoursLecturers
252-0945-17LDoctoral Seminar Machine Learning (HS23) Restricted registration - show details
Only for Computer Science Ph.D. students.

This doctoral seminar is intended for PhD students affiliated with the Institute for Machine Learning. Other PhD students who work on machine learning projects or related topics need approval by at least one of the organizers to register for the seminar.
2 credits1SN. He, V. Boeva, J. M. Buhmann, R. Cotterell, T. Hofmann, A. Krause, G. Rätsch, M. Sachan, J. Vogt, F. Yang
AbstractAn 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.
ObjectiveThe 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 / NoticeThis 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.
263-5056-00LApplications of Deep Learning on Graphs Information Restricted registration - show details 4 credits2G + 1AM. Kuznetsova, G. Rätsch
AbstractGraphs are an incredibly versatile abstraction to represent arbitrary structures such as molecules, relational knowledge or social and traffic networks. This course provides a practical overview of deep (representation) learning on graphs and their applications.
ObjectiveMany established deep learning methods require dense input data with a well-defined structure (e.g. an image, a sequence of word embeddings). However, many practical applications deal with sparsely connected and complex data structures, such as molecules, knowledge graphs or social networks. Graph Neural Networks (GNNs) and general representation learning on graphs have recently experienced a surge in popularity because it addresses the challenge to effectively learn representations over said structures. In this course, we aim to understand the fundamental principles of deep (representation) learning on graphs, the similarities and differences to other concepts in deep learning, as well as the unique challenges from a practical point of view. Finally, we provide an overview of recent applications of graph neural networks.
ContentIntroduction to GNN concepts: 1) problem-solving on graphs (node-, edge-, graph-level objectives), structural priors (inductive biases) of graph data, applications for graph learning. 2) Graph Neural Networks: convolutional, attentional, message passing; overview on the zoo of published operators. Relations to Transformers and DeepSets. 3) Expressivity of GNNs. 4) Scalability of Graph Neural Networks: Subsampling, Clustering (Pooling). 5) Augmentations and self-supervised learning on Graphs Application: Drug Discovery, Knowledge graphs, Temporal GNNs, Geometric GNNs, Deep Generative Models for Graphs.
Prerequisites / Notice263-3210-00 Depp Learning or 263-0008-00 Computational Intelligence Lab;
252-0220-00 Introduction to Machine Learning; Statistics/Probability; Programming in Python; Unix Command Line.
263-5100-00LTopics in Medical Machine Learning Restricted registration - show details
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.
2 credits2SG. Rätsch, J. Vogt
AbstractThis seminar discusses recent relevant contributions to the fields of medical machine learning and related areas. Each participant will hold a presentation and lead the subsequent discussion.
ObjectivePreparing and holding a scientific presentation in front of peers is a central part of working in the scientific domain. In this seminar, the participants will learn how to efficiently summarize the relevant parts of a scientific publication, critically reflect its contents, and summarize it for presentation to an audience. The necessary skills to successfully present the key points of existing research work are the same as those needed to communicate own research ideas. In addition to holding a presentation, each student will both contribute to as well as lead a discussion section on the topics presented in the class.
ContentThe topics covered in the seminar are related to recent computational challenges that arise in the medical field, including but not limited to clinical data analysis, interpretable machine learning, privacy considerations, statistical frameworks, etc. Both recently published works contributing novel ideas to the areas mentioned above as well as seminal contributions from the past are on the list of selected papers.
Prerequisites / NoticeKnowledge of machine learning and interest in applications in medicine. ML4H is beneficial as a prior course.