This four-year, $622,992 project grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop methods for making machine learning models more interpretable and reliable. Specifically, researchers at the University of Virginia will investigate the mathematical foundations of deep neural networks, with a focus on geometry and topology, to better understand internal representations.
Computational tools will be designed based on these mathematical insights to improve interpretability and reliability. Techniques for linking a model's representations to interpretable features and for interactive visualization will be tested. Failure identification, mitigation, and prevention strategies will also be explored using geometric and topological analyses. Finally, the developed methods will be applied to aid oncologists in predicting patient outcomes for head and neck cancers using neural networks. The goal is to help translate machine learning to clinical use by addressing current barriers to trust and understanding of model behaviors and decisions.
Generated 1/7/24, 1:30 AM