Cooperative Data-driven Modeling: Addressing Catastrophic Forgetting in Neural Networks

Explore a seminar on cooperative data-driven modeling presented by Miguel Bessa, Associate Professor of Engineering at Brown University, as part of the MICDE Fall 2022 Seminar Series. Delve into the challenges of catastrophic forgetting in deep neural networks and learn about class-incremental learning scenarios where networks process test data without knowing its origin. Discover how this research addresses the gap between human brain capabilities and artificial neural networks in task learning and retention. Moderated by Krishna Garikipati, Professor of Mechanical Engineering and Mathematics and Director of MICDE at the University of Michigan, this 57-minute in-person seminar offers valuable insights into cutting-edge computational discovery research.