Soheil Kolouri, assistant professor of computer science at Vanderbilt University, has received a National Science Foundation CAREER Award to explore ways to make machine learning more efficient and possibly impact the next generation of such methods.
Despite the success of machine learning, scientists say many foundational questions and theoretical aspects remain poorly understood, posing unwanted ramifications associated with such technologies. Critical among these issues is determining how to accurately quantify the uncertainty of machine learning models and discerning when their predictions are trustworthy.
There’s also a need to enhance the efficiency and robustness of these methods, especially when they are required to learn patterns from limited data or demonstrations. To address some of these issues, Kolouri and his team will use the more than $550,000 NSF grant to study the mathematical foundations of machine learning, using tools from optimal transport, integral geometry, and measure theory.
“The foundational tools developed in this project are anticipated to lead to the next generation of machine learning methods, notable for their efficiency, uncertainty awareness, interpretability, and robustness, with potential benefits in healthcare, transportation, and national defense,” said Kolouri, who also directs the Machine Intelligence and Neural Technologies (MINT) Lab at Vanderbilt.
This research will also be integrated with comprehensive education and outreach initiatives to encourage research involvement across academic levels, from high school to graduate studies. Additionally, there will be engagement of disadvantaged groups, including minority and rural serving institutions in Middle Tennessee, and active promotion of diversity and inclusivity in STEM disciplines, particularly in artificial intelligence and machine learning education.
The prestigious five-year CAREER Award honors early career faculty who have the potential to serve as role models in research and education and lead advances in their fields. Kolouri has contributed to numerous Defense Advanced Research Projects Agency (DARPA) proposals in machine learning and has successfully secured a total of nearly $15 million in funding as a principal investigator, including three large DARPA projects.
Contact: Lucas Johnson, lucas.l.johnson@vanderbilt.edu