Machine Learning and Inverse Problems

In many scientific and medical settings, we cannot directly observe images of interest, such as a person’s internal organs, the microscopic structure of materials or cells, or distant stars and galaxies. Rather, we use MRI scanners, microscopes, and satellites to collect indirect data that require sophisticated algorithms to form an image. Historically, these methods have relied on mathematical models of simple image structures to improve the quality and resolution of the resulting images. My group’s work describes recent efforts to harness vast collections of images to train computers to learn more complex models of image structure, yielding more accurate and higher-resolution images than ever. These new methods lead to new insights into designing neural networks in a principled manner to jointly leverage both training data and physical models of how imaging data is collected.

2021 Kirk Lecture:

Deep Equilibrium and Model Adaptation (FOCM Plenary 2021):

IEEE Signal Processing And Computational imagE formation (SPACE) on “Machine Learning and 
Inverse Problems: 
Depth and Adaptation” (video, slides)

Neumann Networks (COLT Plenary 2020):