Distributed Computing
ETH Zurich

Seminar in Deep Neural Networks (FS 2021)


When & Where: Tuesdays 10:15, online
First seminar: 23.02.2021
Last seminar: 01.06.2021
Coordinators: Roger Wattenhofer & Béni Egressy & Oliver Richter

As a seminar participant, you are invited to attend all the talks and make a presentation. Your presentation should be in English. The presentation should last 35 minutes. Please record a video of your presentation and upload it to the polybox the day before your seminar presentation date. Additionally to the presentation, you should facilitate (together with the other student of the same date) the discussion on zoom, which we will hold from 11.30 -12.00.

Links for the Seminar:
Polybox (you should have received the corresponding password per mail)
Feedback Form

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 and other lectures on deep learning.

Presentation & Discussion

The seminar will be exciting if the presentations are exciting. Here is a 2 page guideline how to do a great scientific presentation. Here are some additional guidelines: 1, 2 and 3. You can find further guidance to structure your talk as well as resources and ideas about what each topic should address here.

We further 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. These are all scientific papers, but if you have been in science long enough...

COVID-19 Situation

Due to the COVID-19 outbreak we will hold the seminar in digital form, with discussions over zoom. All talks can be found here (you should have received the corresponding password per mail). Please have your presentation ready as video the day before your assigned presentation date.


Your grade will mostly depend on your presentation. In addition, we also grade how actively you participate in the discussions throughout the whole semester.

How To Sign Up

There will be two presentation per week, so there is a limited number of slots (topics) which will be assigned based on preference. If you have not received a mail so far, confirming your spot in the seminar, write a sentence regarding your background (courses, projects, ...) in deep learning to Béni Egressy, to get a spot on the waiting list, in case someone cancels.

After You Got Your Topic

We established the following rules to ensure a high quality of the talks and hope that these will result in a good grade for you:


Date Presenter(s) Title Mentor Slides
23.02.2021 Béni Egressy, Oliver Richter Introduction [pdf]
02.03.2021 Jonas Bokstaller
Oliver Richter
Deep Learning and Neural Architecture
Limitations of Deep Learning
Zhao Meng [pptx]
09.03.2021 Neville Walo
Pareek Anuj
NLP: Benchmarks/Tasks/Metrics
NLP: Embeddings
Zhao Meng [pdf]
16.03.2021 Fatjon Zogaj, Mihai Zorca NLP: Attention/BERT/GPT Damian Pascual [pdf][pdf]
23.03.2021 Peter Müller
Rafael Sterzinger
RL: Planning in games
RL: Games with Imperfect Information
Oliver Richter [pdf]
30.03.2021 Arman Raayatsanati, Yu Hong RL: Model based vs. model free DRL Lukas Faber [pdf][pdf]
13.04.2021 Andrea Mattei, Edoardo Ghignone RL: Hierarchical DRL Béni Egressy [pdf][pdf]
20.04.2021 Tobias Birchler, Davide Plozza RL: Meta-Learning Damian Pascual [pdf][pdf]
27.04.2021 Susanne Keller
Martin Tschechne
GNN: Architectures
GNN: Algorithmic Alignment / Necessity
Lukas Faber [pdf]
04.05.2021 Ahmadreza Yousefkhani
Kei Ishikawa
GNN: Theoretical Limitations
GNN: Oversmoothing
Karolis Martinkus [pdf]
11.05.2021 Harish Rajagopal
Haiwei Xie
GNN: Graph Generation
GNN: Simulation
Karolis Martinkus [pdf]
18.05.2021 Maria Eleni Kadoglou
Sidharth Ramesh
ALG: Combining Algorithms and NNs
ALG: Math
Ard Kastrati [pdf]
25.05.2021 Batuhan Tömekçe
ALG: NN architectures for Algorithm Learning Ard Kastrati [pdf]
01.06.2021 Béni Egressy, Oliver Richter Review Seminar