Back to Search
Start Over
NETT: Solving Inverse Problems with Deep Neural Networks
- Publication Year :
- 2018
-
Abstract
- Recovering a function or high-dimensional parameter vector from indirect measurements is a central task in various scientific areas. Several methods for solving such inverse problems are well developed and well understood. Recently, novel algorithms using deep learning and neural networks for inverse problems appeared. While still in their infancy, these techniques show astonishing performance for applications like low-dose CT or various sparse data problems. However, there are few theoretical results for deep learning in inverse problems. In this paper, we establish a complete convergence analysis for the proposed NETT (network Tikhonov) approach to inverse problems. NETT considers nearly data-consistent solutions having small value of a regularizer defined by a trained neural network. We derive well-posedness results and quantitative error estimates, and propose a possible strategy for training the regularizer. Our theoretical results and framework are different from any previous work using neural networks for solving inverse problems. A possible data driven regularizer is proposed. Numerical results are presented for a tomographic sparse data problem, which demonstrate good performance of NETT even for unknowns of different type from the training data. To derive the convergence and convergence rates results we introduce a new framework based on the absolute Bregman distance generalizing the standard Bregman distance from the convex to the non-convex case.
- Subjects :
- FOS: Computer and information sciences
Computer Science - Machine Learning
010103 numerical & computational mathematics
Bregman divergence
01 natural sciences
Convolutional neural network
Machine Learning (cs.LG)
Theoretical Computer Science
Tikhonov regularization
Convergence (routing)
FOS: Mathematics
Mathematics - Numerical Analysis
0101 mathematics
Mathematical Physics
Sparse matrix
Mathematics
Artificial neural network
business.industry
Applied Mathematics
Deep learning
Numerical Analysis (math.NA)
Inverse problem
Computer Science Applications
010101 applied mathematics
Signal Processing
Artificial intelligence
business
Algorithm
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....f8129b461407f9db04fc926b31a817e6