Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
Matrix Representation of Lie Transform in TensorFlow. / Ivanov, A.; Andrianov, S.; Kulabukhova, N.; Sholokhova, A.; Krushinevskii, E. ; Sboeva, E. .
Proceedings of the 9th International Particle Accelerator Conference. ed. / Shane Koscielniak; Todd Satogata; Volker RW Schaa; Jana Thomson . Geneva : JACoW, 2018. p. 3438-3440.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
}
TY - GEN
T1 - Matrix Representation of Lie Transform in TensorFlow
AU - Ivanov, A.
AU - Andrianov, S.
AU - Kulabukhova, N.
AU - Sholokhova, A.
AU - Krushinevskii, E.
AU - Sboeva, E.
PY - 2018/6
Y1 - 2018/6
N2 - 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.
AB - 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.
KW - network
KW - simulation
KW - storage-ring
KW - GPU
KW - linear-dynamics
KW - network
KW - simulation
KW - storage-ring
KW - GPU
KW - linear-dynamics
U2 - 10.18429/JACoW-IPAC2018-THPAK088
DO - 10.18429/JACoW-IPAC2018-THPAK088
M3 - Conference contribution
SN - 978-3-95450-184-7
SP - 3438
EP - 3440
BT - Proceedings of the 9th International Particle Accelerator Conference
A2 - Koscielniak, Shane
A2 - Satogata, Todd
A2 - Schaa, Volker RW
A2 - Thomson , Jana
PB - JACoW
CY - Geneva
T2 - 9th International Particle Accelerator Conference
Y2 - 29 April 2018 through 4 May 2018
ER -
ID: 47518551