TY - GEN
T1 - Precision Learning
T2 - 24th International Conference on Pattern Recognition, ICPR 2018
AU - Maier, Andreas
AU - Schebesch, Frank
AU - Syben, Christopher
AU - Wurfl, Tobias
AU - Steidl, Stefan
AU - Choi, Jang Hwan
AU - Fahrig, Rebecca
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/26
Y1 - 2018/11/26
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85054080255&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2018.8545553
DO - 10.1109/ICPR.2018.8545553
M3 - Conference contribution
AN - SCOPUS:85054080255
T3 - Proceedings - International Conference on Pattern Recognition
SP - 183
EP - 188
BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 20 August 2018 through 24 August 2018
ER -