Precision Learning: Towards Use of Known Operators in Neural Networks

By Andreas K. Maier, Frank Schebesch, Christopher Syben, Tobias Würfl, Stefan Steidl, Jang-Hwan Choi, R. Fahrig. 2017

35 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Geophysics, Statistical and Nonlinear Physics, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Andreas K. Maier
2. Christian Riess
3. Gary F. Marcus
4. Hector Geffner
5. Blai Bonet
6. D. Gunning

In Statistical and Nonlinear Physics

1. Christian Riess
2. Gary F. Marcus

In Model Architectures

1. Andreas K. Maier
2. Christian Riess
3. Gary F. Marcus
4. Brenden M. Lake
5. Marco Baroni
6. Keith J. Holyoak
7. John E. Hummel
8. Franck Ramus

Citations in the corpus

• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020, background): “§ The good news is that although nativism has often been frowned on in the deep learning community, historically, there are some growing signs of a greater openness to “priors” (e.g., Burgess et al., 2019; Rabinowitz et al., 2018; Maier et al., 2017).”
• A Gentle Introduction to Deep Learning in Medical Image Processing (2018, methodology): “Precision learning is a strategy to include known operators into the learning process [60].”