RT info:eu-repo/semantics/article
T1 Comparative study of neural network frameworks for the next generation of adaptive optics systems
A1 González Gutiérrez, Carlos
A1 Santos, Jesús Daniel
A1 Martínez Zarzuela, Mario
A1 Basden, Alistair
A1 Osborn, James
A1 Díaz Pernas, Francisco Javier
A1 Cos Juez, Francisco Javier de
K1 Adaptive optics
K1 Neural networks
K1 Tomographic reconstructor
K1 Parallel processing
K1 33 Ciencias Tecnológicas
AB Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named “CARMEN” are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances.
PB MDPI
YR 2017
FD 2017
LK https://uvadoc.uva.es/handle/10324/56704
UL https://uvadoc.uva.es/handle/10324/56704
LA eng
NO Sensors, 2017, vol. 17, n. 6, p. 1263
NO Producción Científica
DS UVaDOC
RD 24-nov-2024