Acta Numerica· 2019Q1· Review
Solving inverse problems using data-driven models
- 673citations
- Q1SCImago
- 2019year
Short summary
This survey paper reviews recent advances in combining data-driven models, particularly deep learning, with domain-specific physical knowledge to solve ill-posed inverse problems.
AI-generated from the title and abstract; the full text is not read.
Key points
- Inverse problems are fundamental to many scientific and engineering applications.
- Deep learning is being combined with physical models to address ill-posed inverse problems.
- This approach aims to improve the mathematical coherence and practical solvability of these problems.
- The survey covers main contributions in data-driven inverse problems.
AI-generated from the title and abstract; the full text is not read.
Abstract
Recent research in inverse problems seeks to develop a mathematically coherent foundation for combining data-driven models, and in particular those based on deep learning, with domain-specific knowledge contained in physical–analytical models. The focus is on solving ill-posed inverse problems that are at the core of many challenging applications in the natural sciences, medicine and life sciences, as well as in engineering and industrial applications. This survey paper aims to give an account of some of the main contributions in data-driven inverse problems.
The authors' abstract, as published at the source. Acta Numerica, 2019 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Mathematical Physics
Mathematical PhysicsMathematics