Lab Home | Phone | Search
	Center for Nonlinear Studies
	Home  ▶ People   CNLS Staff Members   Executive Committee   Postdocs   Visitors   Students   Research   Publications  ▶ Conferences   Workshops   Sponsorship  ▶ Talks   Seminars   Postdoc Seminars Archive   Quantum Lunch   Quantum Lunch Archive   P/T Colloquia   Archive   Ulam Scholar   Anastasio Fellow   Fellow Program    ▶ Student Requests        Student Program  ▶ Visitor Requests   Description   Past Visitors  ▶ Services   General     History of CNLS     Maps, Directions   T-Division   LANL				Monday, December 16, 20191:30 PM - 2:30 PMCNLS Conference Room (TA-3, Bldg 1690) Seminar Learning to reconstruct images from their measurements Michael McCannMichigan State University When the first convolutional neural network (CNN)-based method entered the ImageNet Large-Scale Visual Recognition Challenge in 2012, its error rate was 15.3%, as compared to 25.8% for the 2011 winner. In subsequent competitions, the majority of the entries (and all of the winners) were CNN-based and continued to improve substantially, with the 2017 winner achieving an error rate of just 2.25%. Following this success, a plethora of CNN-based approaches are now being applied to a wide variety of problems in image processing, including image reconstruction problems. In this talk, I will try to provide a broader context for this trend as well as discuss my work on using learning to reconstruct images from their measurements in the context of X-ray computed tomography. Host: Marc Klasky