Federal Project Grant Award Summary

Georgia TECH Research Corp received a $246,901 CAREER (Faculty Early Career Development) Project Grant from the National Science Foundation's Division of Mathematical Sciences under the Mathematical and Physical Sciences program (CFDA 47.049) on June 1, 2026, with completion targeted for May 31, 2031. The award supports the development of theoretically guaranteed, structure-informed machine learning methodologies and computational tools designed to improve artificial intelligence performance when working with limited, noisy, or incomplete datasets. The primary deliverables include new mathematical foundations and computational algorithms that integrate known structural information—such as symmetries, low-dimensional patterns, and physical constraints—into machine learning models, with particular emphasis on generative models and diffusion models. Additionally, the project will develop methods for discovering hidden structure directly from data, including conservation laws and governing principles of dynamical systems applicable to challenging scientific domains such as turbulence modeling, molecular design, medical imaging, and complex physical systems analysis.

The award incorporates substantial education and workforce development components aligned with the NSF's broader impacts requirement. Deliverables include new courses, undergraduate research opportunities, data science bootcamps, open-source software tools, and outreach activities targeting students in grades 8 through 12. These educational initiatives are designed to broaden participation in STEM fields and prepare students for careers at the intersection of mathematics, computing, and science, while strengthening the mathematical foundations required for future scientific and engineering applications in artificial intelligence.