Distributed Computing
ETH Zurich

Seminar in Deep Neural Networks (FS 2022)

Organization

The Seminar is now running. All participants should have received a confirmatory email by this point. If you wish to join the waiting list in case someone cancels, please write a sentence regarding your background (courses, projects, ...) in deep learning and send it to Peter Belcák.

When & Where: Tuesdays 10:15, ETZ G 91.
First seminar: 22.02.2021.
Last seminar: 31.05.2021.
Coordinators: Roger Wattenhofer, Peter Belcák, Béni Egressy.

As a seminar participant, you are asked to attend all the talks and make a presentation.

Here is the link to the seminar's Moodle course. You can use Moodle to ask questions or start discussions.

Here is the link to the seminar's Polybox repository. You should have received the password by email. You should upload the slides for your talk the day before it is scheduled.

Disclaimer: This is a seminar, we will focus on reasearch and skip most of the basics. If you feel like you cannot follow the discussions we invite you to check out this lecture or other lectures on deep learning. We also recommend Chollet, Francois: Deep learning with Python. 2nd Edition. Simon and Schuster, 2021.

Presentation & Discussion

Your presentation should be in English. The presentation should last exactly 35 minutes, followed by a discussion. The seminar will be exciting when the talks and discussions are exciting.

Here are some guides and guidelines on scholarly presentations: by Roger Wattenhofer, by Garr Reynolds, and by Cheryl Gore-Felton. As is customary in academia, all work not belonging to the author (including figures, explanations, examples, or equations) must be properly referenced.

We expect the presentation to motivate a lively discussion. We encourage discussions during and after the presentations as a main objective of this seminar. It may help discussions if you also try to be critical about the presented work. Participating in Moodle discussions also counts towards the discussion participation.

COVID-19 Situation

We plan to hold this year's seminar in person. If you find yourself unable to participate (say due to an isolation requirement), get in touch with your mentor at first instance. You might then be asked record a video of your presentation and upload it to polybox the day before your seminar presentation date.

Grade

Your grade will depend on your presentation for the most part. In addition, we also grade how actively you participate in the discussions, both in person and on Moodle, throughout the semester.

Presentation Timeline

We established the following rules to ensure a high quality of the talks:

Schedule

Date Presenter(s) Title Mentor Slides
01.03.2022 Haocheng Yin
Jingyu Liu
Meta-Learning Johannes Oswald [pdf] [pdf]
08.03.2022 Giorgio Piatti
Johannes Weidenfeller
GNN: Basic Architectures
GNN: Theoretical Limitations and Power
Béni Egressy
Karolis Martinkus
[pdf] [pdf]
15.03.2022 York Schlabrendorff
Viviane Potocnik
GNN: More expressive GNNs Béni Egressy [pdf] [pdf]
22.03.2022 S Deepak Narayanan
David Gu
GNN: More expressive GNNs
GNN: Explainability of GNNs
Kenza Amara [pdf] [pdf]
29.03.2022 Julius Schulte
Markus Chardonnet
GNN: Graph Generation
Set Models
Karolis Martinkus [pdf] [pdf]
05.04.2022 Chi-Ching Hsu
Frédéric Odermatt
DnT: Basic Architectures, Ideas, and Metrics
DnT: Specialized Architectures and Theoretical Limitations
Benjamin Estermann [pdf][pdf]
12.04.2022 Alvaro Cauderan
Nathan Corecco
DnT: Downstream Tasks / Applications
NLP: Basic Architectures
Benjamin Estermann
Ard Kastrati
[pdf][pdf]
26.04.2022 Yuanzhi Zhu
Philippe Schläpfer
NLP: Advanced Architectures
NLP: Prompt
Ard Kastrati
Zhao Meng
[pdf][pdf]
03.05.2022 Giacomo Camposampiero
Till Aczel
NLP: Contrastive Learning
NLP+CV: Multimodal Machine Learing
Zhao Meng [pdf][pdf]
10.05.2022 Tongyu Lu
Patrik Matosevic
AL: Program Representations for Learning
AL: Code Search, Code Explanation, Code Completion
Peter Belcák [pdf][pdf]
17.05.2022 Martynas Noruisis
Evgenii Bykovetc
AL: Computational Power, Computational Limits
Reinforcement Learning and Inverse Reinforcement Learning
Peter Belcák
Evgenii Bykovetc
[pdf][pdf]