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 department, 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

 

Dates

The seminar takes place regularly on Thursdays at 10 am at the Fraunhofer-ITWM in room E4.09 (Riemann). Titles and other dates will be added in the course of the year.

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

04.07.2019 Dominik Loroch (Fraunhofer ITWM)
Deep Learning is a Highly Parallelizable Task : Overview on Distributed Deep Learning
More on the talk
11.07.2019 Dushyant Mehta (Max Planck Institute for Informatics)
Emergence of Implicit Filter Sparsity in Convolutional Neural Networks: Examining the Causes and Implications
More on the talk
22.08.2019 Valentin Tschannen (Fraunhofer ITWM)
Adapting Deep Neural Classifiers to New Unlabelled Datasets with Adversarial Regularization
More on the talk
29.08.2019 Dominik Straßel (Fraunhofer ITWM):
AI and the GDPR – Principles to Remember
More on the talk
05.09.2019 Yang Yang (Fraunhofer ITWM):
Parallel Iterative Optimization Algorithms for Large-Scale Empirical Minimization Problem
More on the talk
12.09.2019 Seminar cancelled
19.09.2019 Caroline König (COEVA DATA)
Optimizing Asset Managment Using Machine Learning Approaches
More on the talk
26.09.2019 Seminar cancelled
10.10.2019 Dominik Loroch (Fraunhofer ITWM)
Advanced Deep Learning Acceleration Strategies: An Overview on Recent Papers about Accelerating DL Workloads
More on the talk
17.10.2019 Ricard Durall Lopez (Fraunhofer ITWM)
Few-Shot Attribute Transfer
More on the talk
24.10.2019 Seminar cancelled
31.10.2019 Seminar cancelled
07.11.2019 Seminar cancelled
14.11.2019 Avraam Chatzimichailidis (Fraunhofer ITWM): 
GradVis: Visualization and Second Order Analysis of Optimization Surfaces during the Training of Deep Neural Networks
Raju Ram (Fraunhofer ITWM):
Scalable Hyperparameter Optimization with Lazy Gaussian Processes
More on the talks
28.11.2019 Kalun Ho (Fraunhofer ITWM)
05.12.2019 Sabine Müller (Fraunhofer ITWM) and Alexandra Carpen-Amarie (Fraunhofer ITWM)
19.12.2019 Muhammad Mohsin Ghaffar (TU Kaierslautern)