2000 character limit reached
Uncertainty Aware Deep Learning for Particle Accelerators (2309.14502v1)
Published 25 Sep 2023 in cs.LG and physics.acc-ph
Abstract: Standard deep learning models for classification and regression applications are ideal for capturing complex system dynamics. However, their predictions can be arbitrarily inaccurate when the input samples are not similar to the training data. Implementation of distance aware uncertainty estimation can be used to detect these scenarios and provide a level of confidence associated with their predictions. In this paper, we present results from using Deep Gaussian Process Approximation (DGPA) methods for errant beam prediction at Spallation Neutron Source (SNS) accelerator (classification) and we provide an uncertainty aware surrogate model for the Fermi National Accelerator Lab (FNAL) Booster Accelerator Complex (regression).
- Machine learning and the physical sciences. Rev. Mod. Phys., 91:045002, 2019.
- Machine learning and the physical sciences. Rev. Mod. Phys., 91:045002, Dec 2019.
- Deep Learning. MIT Press, 2016. http://www.deeplearningbook.org.
- Uncertainty quantification and deep ensembles. arXiv, 2020.
- Dropout as a bayesian approximation: Representing model uncertainty in deep learning, 2015.
- Roger Koenker. Asymptotic Theory of Quantile Regression, page 116–150. Econometric Society Monographs. Cambridge University Press, 2005.
- Uncertainty aware ml-based surrogate models for particle accelerators: A study at the fermilab booster accelerator booster complex, 2022.
- Carl Edward Rasmussen. Gaussian Processes in Machine Learning, pages 63–71. Springer Berlin Heidelberg, Berlin, Heidelberg, 2004.
- Simple and principled uncertainty estimation with deterministic deep learning via distance awareness, 2020.
- Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, volume 2. Lille, 2015.
- Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778, 2016.
- Uncertainty aware anomaly detection to predict errant beam pulses in the sns accelerator, 2021.
- BOOSTR: A dataset for accelerator control systems. Data, 6(4):42, 2021.
- Predicting particle accelerator failures using binary classifiers. Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 955, March 2020.
- Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 1025:166064, 2022.