Using GPUs to Speed up a Tomographic Reconstructor Based on Machine Learning
- Carlos González-Gutiérrez 1
- Jesús Daniel Santos-Rodríguez 1
- Ramón Ángel Fernández Díaz 2
- Jose Luis Calvo Rolle 3
- Nieves Roqueñí Gutiérrez 1
- Cos Juez, Francisco Javier de 1
-
1
Universidad de Oviedo
info
-
2
Universidad de León
info
-
3
Universidade da Coruña
info
- Manuel Graña (coord.)
- José Manuel López-Guede (coord.)
- Oier Etxaniz (coord.)
- Álvaro Herrero (coord.)
- Héctor Quintián (coord.)
- Emilio Corchado (coord.)
Éditorial: Springer Suiza
ISBN: 978-3-319-47364-2, 3-319-47364-6, 978-3-319-47363-5, 3-319-47363-8
Année de publication: 2017
Pages: 279-289
Congreso: International Conference on Computational Intelligence in Security for Information Systems (9. 2016. San Sebastián)
Type: Communication dans un congrès
Résumé
The next generation of adaptive optics (AO) systems require tomographic techniques in order to correct for atmospheric turbulence along lines of sight separated from the guide stars. Multi-object adaptive optics(MOAO) is one such technique. Here we present an improved version of CARMEN, a tomographic reconstructor based on machine learning, using a dedicated neural network framework as Torch. We can observe a significant improvement on the training an execution times of the neural network, thanks to the use of the GPU.