Cargando…
Big in Japan: Regularizing Networks for Solving Inverse Problems
Deep learning and (deep) neural networks are emerging tools to address inverse problems and image reconstruction tasks. Despite outstanding performance, the mathematical analysis for solving inverse problems by neural networks is mostly missing. In this paper, we introduce and rigorously analyze fam...
Autores principales: | Schwab, Johannes, Antholzer, Stephan, Haltmeier, Markus |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer US
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7144407/ https://www.ncbi.nlm.nih.gov/pubmed/32308256 http://dx.doi.org/10.1007/s10851-019-00911-1 |
Ejemplares similares
-
Discretization of Learned NETT Regularization for Solving Inverse Problems
por: Antholzer, Stephan, et al.
Publicado: (2021) -
Deep learning for photoacoustic tomography from sparse data
por: Antholzer, Stephan, et al.
Publicado: (2018) -
The residual method for regularizing ill-posed problems
por: Grasmair, Markus, et al.
Publicado: (2011) -
Regularization of inverse problems
por: Engl, Heinz W, et al.
Publicado: (1996) -
Superconducting Magnets for the LHC: Conception, Optimization and Inverse Problem Solving
por: Russenschuck, Stephan
Publicado: (1997)