227-0559-00L  Seminar in Deep Neural Networks

SemesterSpring Semester 2022
LecturersR. Wattenhofer, P. Belcák, B. Egressy
Periodicityyearly recurring course
Language of instructionEnglish
CommentNumber of participants limited to 25.


AbstractIn this seminar participating students present and discuss recent research papers in the area of deep neural networks.
Learning objectiveWe 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 neural networks. The students will learn to read, evaluate and challenge research papers, prepare coherent scientific presentations and lead a discussion on their topic.
ContentThe seminar will cover a range of research directions, with a focus on Graph Neural Networks, Algorithmic Learning, Reinforcement Learning and Natural Language Processing. It will be structured in blocks with each focus area being briefly introduced before presenting and discussing recent research papers. Papers will be allocated to the students based on their preferences.

For more information see www.disco.ethz.ch/courses.html.
Lecture notesSlides of presentations will be made available.
LiteratureThe paper selection can be found on www.disco.ethz.ch/courses.html.
Prerequisites / NoticeIt is expected that students have prior knowledge and interest in machine and deep learning, for instance by having attended appropriate courses.