2021/05/08 by Alexander Scheinker, Scheinker, Alexander, Frederick Cropp +5
Computer Science · Physics and Astronomy · #Accelerator Physics (physics.acc-ph) #Advanced Neural Network Applications #Computational Physics and Python Applications #FOS: Computer and information sciences #FOS: Physical sciences #Gamma-ray bursts and supernovae #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.2105.03584
openalex publication_date 2021/05/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Powerful deep learning tools, such as convolutional neural networks (CNN), are able to learn the input-output relationships of large complicated systems directly from data. Encoder-decoder deep CNNs are able to extract features directly from images, mix them with scalar inputs within a general low-dimensional latent space, and then generate new complex 2D outputs which represent complex physical phenomenon. One important challenge faced by deep learning methods is large non-stationary systems whose characteristics change quickly with time for which re-training is not feasible. In this paper we present a method for adaptive tuning of the low-dimensional latent space of deep encoder-decoder style CNNs based on real-time feedback to quickly compensate for unknown and fast distribution shifts. We demonstrate our approach for predicting the properties of a time-varying charged particle beam in a particle accelerator whose components (accelerating electric fields and focusing magnetic fields) are also quickly changing with time.