Mathematics and Deep Learning (MDL) Collective Seminar: Solving Inverse Problems with Deep Learning
Author: Lona | Image: Lona
Speaker: Lexing Ying (Stanford University)
Abstract: This talk is about some recent progress on solving inverse problems using deep learning. Compared to traditional machine learning problems, inverse problems are often limited by the size of the training data set. We show how to overcome this issue by incorporating mathematical analysis and physics into the design of neural network architectures.