English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The solution of linear inverse problems arising, for example, in signal andimage processing is a challenging problem since the ill-conditioning amplifiesthe noise on the data. Recently introduced algorithms based on deep learningoverwhelm the more traditional model-based approaches, but they typicallysuffer from instability with respect to data perturbation. In this paper, wetheoretically analyze the trade-off between neural networks stability andaccuracy in the solution of linear inverse problems. Moreover, we proposedifferent supervised and unsupervised solutions to increase network stabilitythat maintains good accuracy by inheriting, in the network training,regularization from a model-based iterative scheme. Extensive numericalexperiments on image deblurring confirm the theoretical results and theeffectiveness of the proposed deep learning-based solutions to stably solvenoisy inverse problems.

To be or not to be stable, that is the question: understanding neural networks for inverse problems