This $113,018 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) to Michigan State University (MSU) aims to develop robust machine learning methods for image reconstruction and data correction in various imaging applications. The project will focus on advancing supervised and unsupervised learning approaches that can operate effectively with limited training data, while being robust to measurement artifacts, training-test variations, and distribution shifts. The research will explore techniques that leverage sparsity and prior information to improve performance in medical imaging (MRI, CT), electroencephalography (EEG), and other imaging domains. In parallel, the award will support an educational program to increase participation from underrepresented groups in machine learning-driven imaging research. The project period runs from April 1, 2025 to March 31, 2030.