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.)
Verlag: Springer Suiza
ISBN: 978-3-319-47364-2, 3-319-47364-6, 978-3-319-47363-5, 3-319-47363-8
Datum der Publikation: 2017
Seiten: 279-289
Kongress: International Conference on Computational Intelligence in Security for Information Systems (9. 2016. San Sebastián)
Art: Konferenz-Beitrag
Zusammenfassung
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.