Seminar in Deep Neural Networks (FS 2021)
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.
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...
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 TopicWe established the following rules to ensure a high quality of the talks and hope that these will result in a good grade for you:
- At least 5 weeks before your talk: first meeting with your mentor (you need to read the assigned literature before this meeting).
- At least 3 weeks before your talk: meet your mentor to discuss the structure of your talk.
- At least 1 week before your talk: give the talk in front of your mentor who will provide feedback.
- At the presentation date we expect an electronic copy of your slides.
|23.02.2021||Béni Egressy, Oliver Richter||Introduction||[pdf]|
|Deep Learning and Neural Architecture
Limitations of Deep Learning
|16.03.2021||Fatjon Zogaj, Mihai Zorca||NLP: Attention/BERT/GPT||Damian Pascual||[pdf][pdf]|
|RL: Planning in games
RL: Games with Imperfect Information
|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]|
GNN: Algorithmic Alignment / Necessity
|GNN: Theoretical Limitations
|GNN: Graph Generation
|18.05.2021||Maria Eleni Kadoglou
|ALG: Combining Algorithms and NNs
||ALG: NN architectures for Algorithm Learning||Ard Kastrati||[pdf]|
|01.06.2021||Béni Egressy, Oliver Richter||Review Seminar|