Matrix Representation of Lie Transform in TensorFlow

Результат исследований: Публикации в книгах, отчётах, сборниках, трудах конференцийстатья в сборнике материалов конференциинаучнаярецензирование

Аннотация

In the article, we propose an implementation of the matrix representation of Lie transform using TensorFlow as a computational engine. TensorFlow allows easy description of deep neural networks and provides automatic code execution on both single CPU/GPU and cluster architectures. In this research, we demonstrate the connection of the matrix Lie transform with polynomial neural networks. The architecture of the neural network is described and realized in code. In terms of beam dynamics, the proposed technique provides a tool for both simulation and analysis of experimental results using modern machine learning techniques. As a simulation technique one operates with a nonlinear map up to the necessary order of nonlinearity. On the other hand, one can utilize TensorFlow engine to run map optimization and system identification problems.
Язык оригиналаанглийский
Название основной публикацииProceedings of the 9th International Particle Accelerator Conference
РедакторыShane Koscielniak, Todd Satogata, Volker RW Schaa, Jana Thomson
Место публикацииGeneva, Switzerland
ИздательJACoW
Страницы3438-3440
Число страниц3
ISBN (печатное издание)978-3-95450-184-7
DOI
СостояниеОпубликовано - июн 2018

Ключевые слова

  • network
  • simulation
  • storage-ring
  • GPU
  • linear-dynamics

Fingerprint Подробные сведения о темах исследования «Matrix Representation of Lie Transform in TensorFlow». Вместе они формируют уникальный семантический отпечаток (fingerprint).

  • Цитировать

    Ivanov, A., Andrianov, S., Kulabukhova, N., Sholokhova, A., Krushinevskii, E., & Sboeva, E. (2018). Matrix Representation of Lie Transform in TensorFlow. В S. Koscielniak, T. Satogata, V. RW. Schaa, & J. Thomson (Ред.), Proceedings of the 9th International Particle Accelerator Conference (стр. 3438-3440). JACoW. https://doi.org/10.18429/JACoW-IPAC2018-THPAK088