Details of the talk:
- Date: November 30th
- Time: 11:00 a.m. - 12:00 p.m.
- Location: Ground-floor lecture hall, Tübingen AI Center (Maria-von-Linden-Str. 6, 72076 Tübingen)
Talk title: Permutations in Neural Networks and Quantum Annealing
Abstract: Permutations arise in all applications with data that is not naturally ordered, for example, the vertices in a point cloud which are stored in arbitrary order. Extracting the mapping between two instances is often a requirement for downstream tasks. However, optimizing for permutations is complicated due to their discrete nature and complicated constraints which do not scale well. In this talk I will introduce a new representation for permutations that allow for continuous optimization which can be used in neural networks and in addition does not require the storage of a quadratic permutation matrix. Additionally, I will give an introduction to quantum g annealing, which is extremely efficient in solving quadratic unconstrained binary optimization problems, and go over the possibilities of including permutation constraints in this setting.Bio: Zorah Lähner is a postdoc in the Computer Vision group at the University of Siegen and received her PhD in 2021 from the Technical University of Munich. During her PhD she did research internships at Technion Israel Institute of Technology, Facebook Reality Labs, Sapienza Università di Roma, and Toshiba Research Europe. Her research interests are 3D geometry processing, geometric deep learning, and non-rigid shape correspondence. She is funded through the Artificial Intelligence Starter program by the Ministry of Culture and Science of the state of North-Rhine Westphalia. Next year she will start an assistant professorship at the University of Bonn.
Bio: Zorah Lähner is a postdoc in the Computer Vision group at the University of Siegen and received her PhD in 2021 from the Technical University of Munich. During her PhD she did research internships at Technion Israel Institute of Technology, Facebook Reality Labs, Sapienza Università di Roma, and Toshiba Research Europe. Her research interests are 3D geometry processing, geometric deep learning, and non-rigid shape correspondence. She is funded through the Artificial Intelligence Starter program by the Ministry of Culture and Science of the state of North-Rhine Westphalia. Next year she will start an assistant professorship at the University of Bonn. (More info: https://zorah.github.io/.)
We invite all enthusiasts, researchers, and students to join us and dive deep into the realms of AI. Don't miss this great opportunity to continue your learning journey with the Tübingen AI Talk series. See you there!