国家天元数学中部中心高性能计算系列报告 | Dr.Riccardo Barbano(University College London)

发布时间: 2021-01-22 09:45

Title: Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction

Speaker: Dr. Riccardo Barbano University College London

Time: 2021-01-29  17:00-18:00

Zoom ID: 627 7130 1964

Password: 213340

Abstract: Image reconstruction methods based on deep neural networks have shown outstanding performance, equaling, or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the reconstruction. In this talk we propose a scalable and efficient framework to simultaneously quantify aleatoric and epistemic uncertainties in learned iterative image reconstruction.