Last cancellation/deregistration date for this ungraded semester performance: Friday, 18 March 2022! Please note that after that date no deregistration will be accepted and the course will be considered as "fail".
The course will give students an overview of selected topics in advanced machine learning that are currently subjects of active research. The course concludes with a final project.
Lernziel
The overall objective is to give students a concrete idea of what working in contemporary machine learning research is like and inform them about current research performed at ETH.
In this course, students will be able to get an overview of current research topics in different specialized areas. Each topic is accompanied by small hands-on exercises that prepare for the final project. In the final project, students will be able to build experience in practical aspects of machine learning research, including research literature, aspects of implementation, and reproducibility challenges.
Inhalt
The course will be structured as sections taught by different PostDocs specialized in the relevant fields. Each section will showcase an advanced research topic in machine learning, first introducing it and motivating it in the context of current technological or scientific advancement, then providing practical applications that students can experiment with, ideally with the aim of reproducing a very simple, known result in the specific field. The tentative list of topics for this year is 3D scene understanding, graph neural networks, causal discovery, event-based sensors, trustworthy AI, reinforcement learning and visual text analytics. The last weeks of the course will be reserved for the implementation of the final project that the students can select among one of the presented areas.
Voraussetzungen / Besonderes
Participants should have basic knowledge about machine learning and statistics (e.g. Introduction to Machine Learning course or equivalent) and programming.
Leistungskontrolle
Information zur Leistungskontrolle (gültig bis die Lerneinheit neu gelesen wird)
Leistungskontrolle als Semesterkurs