Machine and Deep Learning Seminar

Seminars of the High Performance Center Simulation and Software Based Innovation

Machine Learning, Deep Learning and the analysis of huge amounts of data in general are becoming more and more important. Such methods are used in almost every area of research, development or industry. The Deep Learning Seminar of the Fraunhofer ITWM is intended to give interested persons an insight into this large field of research and a deeper understanding. Everyone who wants to learn more about Deep Learning, Machine Learning or AI in general is invited – no matter if students, PhD students, professors or software developers.

This is a series of seminars within the framework of High Performance Center Simulation and Software Based Innovation.

 

Speakers

In addition to the employees of our division, interested external speakers can also give a lecture in our seminar series. We also have the opportunity to invite external speakers. We are always open to suggestions, suggestions or requests.

 

Lectures and Talks

A talk should have a minimum length of 20 minutes and a maximum length of 60 minutes. The remaining time is available for questions, comments and feedback. We plan a maximum of 60 minutes for each seminar.

The topic of a talk should either come directly from or is relevant to Deep Learning, Machine Learning, Data Analysis or AI, no matter whether it is about a paper, an own project on or an interesting topic. The complexity can range from an overview talk to a special topic.

 

Contact

In addition to the website with current information, we offer a mailing list: Subscribe

General Information about the Dates 2023

The seminar will take place regularly from March on Thursdays at the Fraunhofer ITWM. Titles and other dates will be added in the course of the year.

The talks of our employees of the division are marked with (Fraunhofer ITWM). These dates can be postponed without any problems if there is interest in a lecture on this date.

Dates 2023

Date Title Speaker
04.04.2023 ChatGPT: If Scale is the Answer, What is Left to be Asked? To the lecture Prof. Dr. Goran Glavaš (University of Würzburg, Faculty of Mathematics and Computer Science, Center for Artificial Intelligence and Data Science (CAIDAS))
20.04.2023 Unfolding Local Growth Rate Estimates for(Almost) Perfect Adversarial Detection
To the lecture
Peter Lorenz (Fraunhofer ITWM, Division »High Performance Computing«)
27.04.2023
Can We Train CNNs Without Ever Learning Filters? To the lecture
Paul Gavrikov (Hochschule Offenburg, Institute for Machine Learning and Analytics (IMLA))
04.05.2023 Robust Models Are Less Overconfident To the lecture Julia Grabinski (Fraunhofer ITWM, Division »High Performance Computing«)
11.05.2023 Physics-Constrained Deep Learning for Climate DownscalingTo the lecture Paula Harder (Fraunhofer ITWM, Division »High Performance Computing«)
16.05.2023 Deep Reinforcement Learning To the lecture Prof. Dr. rer. nat. Klaus Dorer (Hochschule Offenburg, Institute for Machine Learning and Analytics (IMLA))
25.05.2023 Deep Learning for Seismic Applications To the lecture Ricard Durall (Fraunhofer ITWM, Division »High Performance Computing«)
07.06.2023 Neural Architecture Search To the lecture Dominik Loroch (Fraunhofer ITWM, Division »High Performance Computing«)
06.07.2023
Breaking the Boundaries of Certified Robustness To the lecture Dr. Andrew Cullen (Departement »Adversarial Machine Learning«, University of Melbourne)
28.09.2023  A Novel Perspective on Robustness in Deep Learning To the lecture Dr. Hadi M. Dolatabadi, Postdoctoral Research Fellow at ARC Center of Excellence for Automated Decision-Making and Society (ADM+S)
19.10.2023 From Spiking Neural Networks to Event-Based AI – the SpiNNaker2 System To the lecture Matthias Lohrmann (Co-Founder and Managing Director of SpiNNcloud Systems)
25.10.2023 Dissecting U-net for Seismic Application To the lecture M.Sc. Ricard Durall Lopez (Member of our division »High Performance Computing«
08.11.2023 Analyzing and Lifting Architectural Constraints on Normalizing Flows To the lecture Felix Matthias Draxler (Computer Science and Mathematics PhD at the University of Heidelberg)
15.11.2023 Permutations in Neural Networks and Quantum Annealing To the lecture Dr. Zorah Lähner (Postdoc at the University of Siegen in the research group »Computer Vision«)
22.11.2023 Deep Learning for Seismic Demultiple To the lecture Mario Ruben Fernandez (Fraunhofer ITWM, Division »High Performance Computing«)
29.11.2023 Deep Geometric Consistent 3D Shape Matching To the lecture Paul Rötzer (PhD Student at the Institute of Computer Science II of the University of Bonn)
06.12.2023 A Case for Coherent Point Sets as Versatile Object Representation To the lecture Dr. Jan Eric Lenssen (Max-Planck Institute for Informatics)
13.12.2023 Synthetic Data for Defect Segmentation on Complex Metal Surfaces To the lecture Juraj Fulir (Fraunhofer ITWM, Department »Image Processing«)