As the number of trained neural network models continues to grow, a fascinating opportunity has emerged to learn from these diverse model populations, known as “model zoos”. In this talk, we will explore the recent advances in “weight spaces learning” aiming to learn representations of model weights and their applications to discriminative and generative downstream tasks. On the discriminative side, such representations enable advanced model analysis such as e.g., the prediction of model performance without requiring access to test data. On the generative side, these representations support the sampling of new, high-performing models for tasks like initialization, transfer learning, and ensemble creation. Attendees will gain insights into not only how weight space learning could be applied in real-world machine learning tasks such as image classification, but also how it could pave a path towards the training of a foundation model of neural networks.
Bio:
Prof. Dr. Damian Borth holds a full professorship in Artificial Intelligence and Machine Learning (AIML) at the University of St.Gallen, Switzerland. Previously, Damian was the founding director of the Deep Learning Competence Center at the German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern, where he was also PI of the NVIDIA AI Lab at the DFKI. His research focuses on representation learning of neural network’s weight spaces and multispectral images. His work has been awarded with the ACM SIGMM Test of Time Award 2023, Google Research Scholar Award 2022, and the NVIDIA AI Lab at NVIDIA GTC 2016. Damian did his postdoctoral research at UC Berkeley and ICSI in Berkeley, where he was involved in big data projects at the Lawrence Livermore National Laboratory. He received his PhD from the University of Kaiserslautern and the German Research Center for Artificial Intelligence (DFKI). During that time, Damian stayed as a visiting researcher at the Digital Video and Multimedia Lab at Columbia University, New York City, USA.
Organizer
AI Lab
Student Host
Martin Ziqiao MaAI Lab Seminar Tsar
Faculty Host
Stella YuProfessor, Computer Science and EngineeringUniversity of Michigan
MENU 
