• español
  • English
  • français
  • Deutsch
  • português (Brasil)
  • italiano
    • español
    • English
    • français
    • Deutsch
    • português (Brasil)
    • italiano
    • español
    • English
    • français
    • Deutsch
    • português (Brasil)
    • italiano
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of UVaDOCCommunitiesBy Issue DateAuthorsSubjectsTitles

    My Account

    Login

    Statistics

    View Usage Statistics

    Share

    View Item 
    •   UVaDOC Home
    • SCIENTIFIC PRODUCTION
    • Departamentos
    • Dpto. Teoría de la Señal y Comunicaciones e Ingeniería Telemática
    • DEP71 - Artículos de revista
    • View Item
    •   UVaDOC Home
    • SCIENTIFIC PRODUCTION
    • Departamentos
    • Dpto. Teoría de la Señal y Comunicaciones e Ingeniería Telemática
    • DEP71 - Artículos de revista
    • View Item
    • español
    • English
    • français
    • Deutsch
    • português (Brasil)
    • italiano

    Export

    RISMendeleyRefworksZotero
    • edm
    • marc
    • xoai
    • qdc
    • ore
    • ese
    • dim
    • uketd_dc
    • oai_dc
    • etdms
    • rdf
    • mods
    • mets
    • didl
    • premis

    Citas

    Por favor, use este identificador para citar o enlazar este ítem:https://uvadoc.uva.es/handle/10324/56704

    Título
    Comparative study of neural network frameworks for the next generation of adaptive optics systems
    Autor
    González Gutiérrez, Carlos
    Santos, Jesús Daniel
    Martínez Zarzuela, MarioAutoridad UVA Orcid
    Basden, Alistair
    Osborn, James
    Díaz Pernas, Francisco JavierAutoridad UVA
    Cos Juez, Francisco Javier de
    Año del Documento
    2017
    Editorial
    MDPI
    Descripción
    Producción Científica
    Documento Fuente
    Sensors, 2017, vol. 17, n. 6, p. 1263
    Abstract
    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.
    Materias Unesco
    33 Ciencias Tecnológicas
    Palabras Clave
    Adaptive optics
    Neural networks
    Tomographic reconstructor
    Parallel processing
    Revisión por pares
    SI
    DOI
    10.3390/s17061263
    Patrocinador
    Ministerio de Economía y Competitividad through grant AYA2014-57648-P
    Gobierno del Principado de Asturias (Consejería de Economía y Empleo), through grant FC-15-GRUPIN14-017
    This work is also funded by the UK Science and Technology Facilities Council, grant ST/K003569/1, and a consolidated grant ST/L00075X/1
    Version del Editor
    https://www.mdpi.com/1424-8220/17/6/1263
    Propietario de los Derechos
    © 2017 The Author(s)
    Idioma
    eng
    URI
    https://uvadoc.uva.es/handle/10324/56704
    Tipo de versión
    info:eu-repo/semantics/publishedVersion
    Derechos
    openAccess
    Collections
    • DEP71 - Artículos de revista [358]
    Show full item record
    Files in this item
    Nombre:
    Comparative-study-neural-network.pdf
    Tamaño:
    2.306Mb
    Formato:
    Adobe PDF
    Thumbnail
    FilesOpen
    Atribución 4.0 InternacionalExcept where otherwise noted, this item's license is described as Atribución 4.0 Internacional

    Universidad de Valladolid

    Powered by MIT's. DSpace software, Version 5.10