Theoretical Foundations of Deep Learning completed

Deep learning is revolutionizing real-world applications and science, replacing or complementing classical model-based methods in solving mathematical problems. Despite successes, deep neural networks lack strong theoretical-mathematical foundations. This program aims to develop a comprehensive theoretical foundation of deep learning from three perspectives: statistical, application, and mathematical-methodological. The research is interdisciplinary, combining mathematics, statistics, and theoretical computer science to address complex questions.

SPP 2298, project number 441826958
May 2020 to May 2023
5

🧑‍🎓 Project Members

Gitta Kutyniok
Principal Investigator
Ingo Steinwart
Principal Investigator
Martin Burger
Principal Investigator
Matthias Hein
Principal Investigator
Sebastian Pokutta
Principal Investigator
pokutta (at) zib.de

🪙 Funding

This project was being funded by the German Research Foundation from May 2020 to May 2023.