This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) provides $472,934 to Northeastern University to address a critical challenge in artificial intelligence (AI) - how to make machine learning more efficient in real-world scientific and engineering settings where data is sparse or imperfect.
The research program focuses on incorporating symmetry, an organizing principle in nature, into machine learning systems in a flexible and adaptable way to handle noisy, real-world data. This will make AI models more efficient and applicable across a range of domains like material discovery, robotics, and climate modeling. Key activities include developing new machine learning architectures that enforce symmetry constraints, establishing mathematical guarantees on model performance, and exploring how relaxing symmetry constraints can improve model optimization. The research outcomes will also include an online course, an interdisciplinary workshop, and outreach programs to engage high school students in AI research.