Amjad, J;
Sokolic, J;
Rodrigues, MRD;
(2018)
On Deep Learning for Inverse Problems.
In:
2018 26th European Signal Processing Conference (EUSIPCO).
(pp. pp. 1895-1899).
IEEE
Preview |
Text
EUSIPCO_amjad18 - CameraReady.pdf - Accepted Version Download (454kB) | Preview |
Abstract
This paper analyses the generalization behaviour of a deep neural networks with a focus on their use in inverse problems. In particular, by leveraging the robustness framework by Xu and Mannor, we provide deep neural network based regression generalization bounds that are also specialized to sparse approximation problems. The proposed bounds show that the sparse approximation performance of deep neural networks can be potentially superior to that of classical sparse reconstruction algorithms, with reconstruction errors limited only by the noise level independently of the underlying data.
| Type: | Proceedings paper |
|---|---|
| Title: | On Deep Learning for Inverse Problems |
| Event: | 26th European Signal Processing Conference (EUSIPCO), 3-7 September 2018, Roma, Italy |
| Location: | Rome, ITALY |
| Dates: | 03 August 2018 - 07 August 2018 |
| ISBN-13: | 978-9-0827-9701-5 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.23919/EUSIPCO.2018.8553376 |
| Publisher version: | https://doi.org/10.23919/EUSIPCO.2018.8553376 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Inverse problems , Neural networks , Robustness , Training , Measurement , Partitioning algorithms , Signal processing algorithms |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10068636 |
Archive Staff Only
 |
View Item |
