Neural operators such as Deep Operator Networks (DeepONet) and Convolutional Neural Operators (CNO) have been shown to be fairly useful in approximating an operator between two function spaces. In this talk, we will briefly review two inverse problems that arise in Medical Imaging, namely EIT and QPAT. We will also describe the relevant operator learning architectures. Subsequently, we will present approximation-theoretic guarantees that provide a justification for using such neural operators for learning (or, approximating) operator maps that arise in the two afore-mentioned inverse problems. This is based on joint works with Thilo Strauss (Xi’an Jiaotong-Liverpool University) and Taufiquar Khan and Sudeb Majee (UNC Charlotte).

Speaker’s Website: https://artscidirectory.case.edu/faculty/anuj-abhishek/