Published on 07.10.2024
From September 23 to 24, 2024, the Deep Learning in Inverse Problems workshop brought together around 70 participants from various Helmholtz centers, and national and international universities for two days of presentations, discussions, and collaborative networking. Organized and supported by DESY, Helmholtz Imaging, the University of Hamburg and the DFG-funded priority programme FoDL, this event served as an important platform for the community to exchange ideas and explore learning-based methods for solving inverse problems.
Key Themes and Discussions
The workshop explored both foundational concepts and practical applications, including supervised and unsupervised learning, learned regularizations, and generative models for Bayesian inversion. Particular emphasis was put on the understanding of foundations of learning in this area as well as novel applications including problems in imaging and speech/audio processing.
Engaging Keynotes and Talks in a Collaborative Atmosphere
Participants had the opportunity to hear from several leading experts in the field. Keynote speakers included:
In addition to the five keynote presentations, the workshop featured 14 contributed talks and nine poster presentations, fostering exchanges and insights into the latest research applications, successes, and challenges. The diverse group of participants shared a common goal of advancing knowledge in inverse problems, making the event a dynamic forum for idea exchange and potential collaborations.
Looking to the Future
The workshop concluded with enthusiasm and optimism about the future of deep learning applications in inverse problems. The knowledge exchanged during the event is expected to drive future research advancements and enhance collaboration within this growing community.
A big thank you to all who contributed to making this event such a success!
**
Stay tuned for more upcoming events! Sign up for our newsletter: https://helmholtz-imaging.de/newsletter/
**
Photos were taken by Knut Sander.