Parallel to the impressive success of deep learning in real-world applications ranging from autonomous driving to gaming intelligence and healthcare, deep learning-based methods are now also making a strong impact in science, replacing or complementing state-of-the-art classical model-based methods in solving mathematical problems such as inverse problems or partial differential equations.
However, despite the outstanding successes, most of the research on deep neural networks is empirically driven and their theoretical-mathematical foundations are largely lacking. The main goal of this priority program is to develop a comprehensive theoretical foundation of deep learning.
The statistical perspective, which views neural network training as a statistical learning problem and investigates expressivity, learning, optimization, and generalization,
The application perspective, which focuses on security, robustness, interpretability, and fairness
The mathematical-methodological perspective, which develops and theoretically analyzes novel Deep Learning-based approaches to solving inverse problems and partial differential equations.
The research questions to be addressed in this priority program are to a large extent interdisciplinary in nature and can only be solved by a joint effort of mathematics and computer science.
Mathematical methods and concepts from all areas of mathematics are required, including algebraic geometry, analysis, stochastics, approximation theory, differential geometry, discrete mathematics, functional analysis, optimal control, optimization, and topology.
Statistics and theoretical computer science also play a fundamental role. In this sense, methods from mathematics, statistics and computer science form the core of this priority program.
The 2023 annual meeting was a valuable platform for showcasing the various research endeavors of the SPP. The beautiful atmosphere of Lake Starnberg provided an inspiring backdrop for the event, creating an ideal setting for the exchange of ideas and fruitful discussions.
.png)
An information session for phase 2 of the priority program took place on the 18th of October. Please click the links below to download the slides.
If you are interested in joining Phase 2 of the Theoretical Foundations of Deep Learning Prioritiy Program, please click below to find out more about how to apply.
For the preparation, please consider the following points:
1 -Add the connection to the priority program and why your project fits into the scope.
2 -Note that the reviewers will look at the posters digitally or print them in DIN A4. Hence, your design should work well in this setting.
3 -Publications which were published after the submission can be included in the poster.
4 -The poster is an opportunity to present your work in a compact and concise way.
Find the latest news and upcoming events from the various groups researching artificial intelligence and its applications at LMU Munich.
