Progress Towards Machine Learning Phasing for Bragg Coherent Diffractive Imaging
Institute for Pure & Applied Mathematics (IPAM) via YouTube
Google AI Professional Certificate - Learn AI Skills That Get You Hired
Learn Backend Development Part-Time, Online
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore the potential of machine learning approaches in solving the crystallographic "phase problem" for Bragg Coherent Diffractive Imaging (BCDI) in this 43-minute lecture by Ian Robinson from Brookhaven National Laboratory. Delve into the challenges of reconstructing sample density and strain information from X-ray diffraction patterns, and learn about the limitations of current iterative algorithms. Discover the latest progress in applying deep neural networks to both 2D and 3D coherent X-ray imaging data, with references to key publications in the field. Gain insights into the fundamental principles of BCDI, the Shannon Information Theorem, and the ongoing efforts to overcome stagnation and multiple solution issues in phase retrieval methods.
Syllabus
Ian Robinson - Progress towards Machine Learning Phasing for Bragg Coherent Diffractive Imaging
Taught by
Institute for Pure & Applied Mathematics (IPAM)