Elenco seminari del ciclo di seminari
“PRIOR LEARNING FOR SOLVING INVERSE PROBLEMS”

This teaching unit introduces a computational "toolbox" for learning priors in the context of solving Bayesian inverse problems in imaging. The tools covered include methods for learning optimal discretizations of total-variation related regularization terms, explicit diffusion models based on products of 1D Gaussian mixture models, and the application of the maximum entropy principle for learning generative priors.
Giugno
04
2025
Thomas Pock
Prior learning for solving inverse problems
nel ciclo di seminari: PRIOR LEARNING FOR SOLVING INVERSE PROBLEMS
analisi numerica
This teaching unit introduces a computational "toolbox" for learning priors in the context of solving Bayesian inverse problems in imaging. The tools covered include methods for learning optimal discretizations of total-variation related regularization terms, explicit diffusion models based on products of 1D Gaussian mixture models, and the application of the maximum entropy principle for learning generative priors.
organizzato da: INTERNATIONAL PHD SUMMER SCHOOL "MATHEMATICS AND MACHINE LEARNING FOR IMAGE ANALYSIS "
nell'ambito del Progetto Fondi U.E. BPIS_2023_MORIGI Mathematics and Machine Learning for image analysis (ERASMUS+) del prof. Serena Morigi