Precision Learning: Towards Use of Known Operators in Neural Networks

Andreas Maier, Frank Schebesch, Christopher Syben, Tobias Wurfl, Stefan Steidl, Jang Hwan Choi, Rebecca Fahrig

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

24 Scopus citations

Abstract

In this paper, we consider the use of prior knowledge within neural networks. In particular, we investigate the effect of a known transform within the mapping from input data space to the output domain. We demonstrate that use of known transforms is able to change maximal error bounds and that these are additive for the entire sequence of transforms. In order to explore the effect further, we consider the problem of X-ray material decomposition as an example to incorporate additional prior knowledge. We demonstrate that inclusion of a non-linear function known from the physical properties of the system is able to reduce prediction errors therewith improving prediction quality from SSIM values of 0.54 to 0.88. This approach is applicable to a wide set of applications in physics and signal processing that provide prior knowledge on such transforms. Also maximal error estimation and network understanding could be facilitated using this novel concept of precision learning.

Original languageEnglish
Title of host publication2018 24th International Conference on Pattern Recognition, ICPR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages183-188
Number of pages6
ISBN (Electronic)9781538637883
DOIs
StatePublished - 26 Nov 2018
Event24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
Duration: 20 Aug 201824 Aug 2018

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2018-August
ISSN (Print)1051-4651

Conference

Conference24th International Conference on Pattern Recognition, ICPR 2018
Country/TerritoryChina
CityBeijing
Period20/08/1824/08/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Fingerprint

Dive into the research topics of 'Precision Learning: Towards Use of Known Operators in Neural Networks'. Together they form a unique fingerprint.

Cite this