Cooperative Data-driven Modeling: Addressing Catastrophic Forgetting in Neural Networks
Offered By: MICDE University of Michigan via YouTube
Course Description
Overview
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.
Syllabus
Miguel Bessa: Cooperative Data-driven Modeling
Taught by
MICDE University of Michigan
Related Courses
Active Dendrites Avoid Catastrophic Forgetting - Interview With the AuthorsYannic Kilcher via YouTube Avoiding Catastrophe - Active Dendrites Enable Multi-Task Learning in Dynamic Environments
Yannic Kilcher via YouTube Supermasks in Superposition - Paper Explained
Yannic Kilcher via YouTube What Kind of AI Can Help Manufacturing Adapt to a Pandemic
Open Data Science via YouTube Rethinking Architecture Design for Data Heterogeneity in FL - Liangqiong Qu
Stanford University via YouTube