Mumin Jin is a PhD candidate whose research integrates signal processing, machine learning, and array processing to significantly expand the capabilities of sensing systems for radio frequency, acoustic, and other modalities for a host of contemporary applications. Specifically, Mumin is applying machine learning to problems in sparse signal approximation and array processing, and working to train neural networks to enhance automotive radar imaging in autonomous vehicles. A key element of her current research, supported by a MathWorks Fellowship, is her use of machine learning to create powerful high-dimensional priors on the scenes being imaged by radar systems. MathWorks toolkits including Phased Array and Autonomous Driving are essential to her work, which has yielded additional tools useful for the radar community. Mumin’s innovative research has the potential to significantly advance the use of machine learning in sparse signal reconstruction and array processing problems in autonomous vehicles and a variety of other applications, and inspire other researchers to explore strategies for integrating machine learning and signal processing.