Current Topics in Machine Learning and Computational Neuroscience

In this seminar recent deep learning papers will be presented and discussed. The goal is to dive deeper into deep learning topics beyond what can be covered in a lecture and also to give an insight in recent research topics in our lab.

We will announce more details about the specific topics around two weeks before the semester starts.

Recommended previous knowledge

• B.Inf.1236 Machine Learning
• B.Inf.1237 Deep Learning for Computer Vision (the seminar can accompany lecture in the same term)

Examination

• Oral presentation (approx. 25 min.) and term paper (max. 3 pages)
• Examination requirements
  • Knowledge in a specific field of machine learning (acquired during the seminar)
  • Ability to present the acquired knowledge in a both orally and in a written report

Organization

There will be a starting session where the topics are presented. In the following week we give you an introduction in how to present and give feedback. In the next weeks, in each weekly session, one paper will be presented (25 minutes) and subsequently discussed (~15 minutes) and the other slot will be a trial presentation of the presenter of the following week.

Our plan is to hold this seminar in presence in room PC Pool 2.164 (Goldschmidtstr. 1) on Mondays 10:15 - 11:45.

If you are interested in this course, please register at Stud.IP.

Topics

• In-context learning
• Learning neural reprsentation
• Implicit shape models / neural implicit fields
• How to solve PDEs using neural networks?
• Multi-modal models: Chemleon & TRIBE
• Multi-view action recognition
• Test-time training
• Token merging
• Part-whole hierarchies
• Synchronization models