IDP presentation. Hanady is advised by Dr. Felix Dietrich.
The SCCS Colloquium is a forum giving students, guests, and members of the chair the opportunity to present their research insights, results, and challenges. Do you need ideas for your thesis topic? Do you want to meet your potential supervisor? Do you want to discuss your research with a diverse group of researchers, rehearse your conference talk, or simply cheer for your colleagues? Then this is the right place for you (and you are also welcome to bring your friends along).
Hanady Gebran: Infinitely wide transformer networks and their Laplace operators
SCCS Colloquium |
We investigate the relationship between neural network Gaussian process kernels (NNGP) for infinitely large transform neural network architectures, and Laplace operators on the data sets where these networks are typically applied. NNGPs are equivalent to Bayesian neural networks in a particular limit, and provide a closed form for evaluation on new data points. This kernel is available for many network architectures, and we briefly study which kernels correspond to which networks, focusing on transformer networks. The integral operator equipped with the NNGP kernel of an infinite-width transform network spectrum is then studied and the transformation between bases is considered to derive the geometry induced on the data via the Laplace Beltrami operator. This induction is possible because all NNGP kernels are symmetric positive semidefinite kernels and thus can be used to span functional spaces on the data manifold on which the original network was trained. The Laplacian-based manifold learning approach is justified by the fact that the Laplace-Beltrami operator encodes all geometric information of a Riemannian manifold.
Contribute a talk
To register and schedule a talk, you should fill the form Colloquium Registration at least two weeks before the earliest preferred date. Keep in mind that we only have limited slots, so please plan your presentation early. In special cases, contact firstname.lastname@example.org.
Note: Starting from October, Colloquium sessions will be on-campus. We have booked room MI 00.13.054. You can either bring your own laptop (please bring your own adapters) or send us the slides as a PDF ahead of time.
We invite students doing their Bachelor's or Master's thesis, as well as IDP, Guided Research, or similar projects at SCCS to give one 20min presentation to discuss their results and potential future work. The time for this is typically after submitting your final text. Check also with your study program regarding any requirements for a final presentation of your project work.
New: In regular times, we will now have slots for presenting early stage projects (talk time 2-10min). This is an optional opportunity for getting additional feedback early and there is no strict timeline.
Apart from students, we also welcome doctoral candidates and guests to present their projects.
During the colloquium, things usually go as follows:
- 10min before the colloquium starts, the speakers setup their equipment with the help of the moderator. The moderator currently is Irene López. Make sure to be using an easily identifiable name in the online session's waiting room.
- The colloquium starts with an introduction to the agenda and the moderator asks the speaker's advisor/host to put the talk into context.
- Your talk starts. The scheduled time for your talk is normally 20min with additional 5-10min for discussion.
- The moderator keeps track of the time and will signal 2min before the end of time (e.g. by turning on their video).
- During the discussion session, the audience can ask questions, which are meant for clarification or for putting the talk into context. The audience can also ask questions in the chat.
- Congratulations! Your talk is over and it's now time to celebrate! Have you already tried the parabolic slides that bring you from the third floor to the Magistrale?
Do you remember a talk that made you feel very happy for attending? Do you also remember a talk that confused you? What made these two experiences different?
Here are a few things to check if you want to improve your presentation:
- What is the main idea that you want people to remember after your presentation? Do you make it crystal-clear? How quickly are you arriving to it?
- Which aspects of your work can you cover in the given time frame, with a reasonable pace and good depth?
- What can you leave out (but maybe have as back-up slides) to not confuse or overwhelm the audience?
- How are you investing the crucial first two minutes of your presentation?
- How much content do you have on your slides? Is all of it important? Will the audience know which part of a slide to look at? Will somebody from the last row be able to read the content? Will somebody with limited experience in your field have time to understand what is going on?
- Are the figures clear? Are you explaining the axes or any other features clearly?
In any case, make sure to start preparing your talk early enough so that you can potentially discuss it, rehearse it, and improve it.
Here are a few good videos to find out more:
- Simon Peyton Jones: How to Give a Great Research Talk (see also How to Write a Great Research Paper)
- Susan McConnell: Designing effective scientific presentations
- Jens Weller: Presenting Code
Did you know that the TUM English Writing Center can also help you with writing good slides?
Work with us!
Do your thesis/student project in Informatics / Mathematics / Physics: Student Projects at the SCCS.