Solving inverse problems using data-driven models

被引：363
|
作者：
Arridge, Simon [1 ]
Maass, Peter [2 ]
Oktem, Ozan [3 ]
Schonlieb, Carola-Bibiane [4 ]
机构：
[1] UCL, Dept Comp Sci, Gower St, London WC1E 6BT, England
[2] Univ Bremen, Dept Math, Postfach 330 440, D-28344 Bremen, Germany
[3] KTH Royal Inst Technol, Dept Math, SE-10044 Stockholm, Sweden
[4] Univ Cambridge, Dept Appl Math & Theoret Phys, Wilberforce Rd, Cambridge CB3 0WA, England
来源：
ACTA NUMERICA | 2019年 / 28卷
基金：
英国工程与自然科学研究理事会;
关键词：
LOW-DOSE CT; CONVOLUTIONAL NEURAL-NETWORKS; ILL-POSED PROBLEMS; GENERATIVE ADVERSARIAL NETWORK; POSTERIOR CONTRACTION RATES; IMAGE-RESTORATION; CONVERGENCE-RATES; SIGNAL RECOVERY; REGULARIZATION METHODS; TIKHONOV REGULARIZATION;
D O I：
10.1017/S0962492919000059
中图分类号：
O1 [数学];
学科分类号：
0701 ; 070101 ;
摘要：
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.
引用
收藏
页码：1 / 174
页数：174
相关论文
共 50 条
  • [21] Data-Driven Problems in Elasticity
    Conti, S.
    Mueller, S.
    Ortiz, M.
    ARCHIVE FOR RATIONAL MECHANICS AND ANALYSIS, 2018, 229 (01) : 79 - 123
  • [22] Data-Driven Problems in Elasticity
    S. Conti
    S. Müller
    M. Ortiz
    Archive for Rational Mechanics and Analysis, 2018, 229 : 79 - 123
  • [23] End-to-end reconstruction meets data-driven regularization for inverse problems
    Mukherjee, Subhadip
    Carioni, Marcello
    Oktem, Ozan
    Schonlieb, Carola-Bibiane
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [24] Data-driven designs of observers and controllers via solving model matching problems
    Chen, Hongtian
    Luo, Hao
    Huang, Biao
    Jiang, Bin
    Kaynak, Okyay
    AUTOMATICA, 2023, 156
  • [25] Formulating and heuristic solving of contact problems in hybrid data-driven computational mechanics
    Gebhardt, Cristian G.
    Lange, Senta
    Steinbach, Marc C.
    COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION, 2024, 134
  • [26] Monthly prediction of streamflow using data-driven models
    Yaghoubi, Behrouz
    Hosseini, Seyed Abbas
    Nazif, Sara
    JOURNAL OF EARTH SYSTEM SCIENCE, 2019, 128 (06)
  • [27] Monthly prediction of streamflow using data-driven models
    Behrouz Yaghoubi
    Seyed Abbas Hosseini
    Sara Nazif
    Journal of Earth System Science, 2019, 128
  • [28] Estimation of infiltration rate using data-driven models
    Sepahvand A.
    Singh B.
    Ghobadi M.
    Sihag P.
    Arabian Journal of Geosciences, 2021, 14 (1)
  • [29] Data-driven Stellar Models
    Green, Gregory M.
    Rix, Hans-Walter
    Tschesche, Leon
    Finkbeiner, Douglas
    Zucker, Catherine
    Schlafly, Edward F.
    Rybizki, Jan
    Fouesneau, Morgan
    Andrae, Rene
    Speagle, Joshua
    ASTROPHYSICAL JOURNAL, 2021, 907 (01):
  • [30] Integration of planning, scheduling and control problems using data-driven feasibility analysis and surrogate models
    Dias, Lisia S.
    Ierapetritou, Marianthi G.
    COMPUTERS & CHEMICAL ENGINEERING, 2020, 134
12345