Computer vision: Easy on the eyes.

In the current issue of the Proceedings of the National Academy of Sciences, Dr. Thomas Serre describes how he and his colleagues at the Massachusetts Institute of Technology have built a computer that can recognize classes of things as accurately as a person can. Although computers are very good a...

Descripción completa

Detalles Bibliográficos
Publicado en:Economist Vol. 383; pp. 77 - 79
Formato: Artículo
Publicado: Economist Newspaper Limited April 7 2007
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=507971267&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 507971267
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00130613
        ECO
      jtl: Economist
      issn: 00130613
      maglogo: N
    pubinfo:
      dt: April 7 2007
      vid: 383
      pid: 161
      pub: Economist Newspaper Limited
    artinfo:
      ui: 507971267
      ppf: 77
      ppct: 2
      formats:
      tig:
        atl: Computer vision: Easy on the eyes.
      aug:
      su: Optical computing
      sug:
        subj: Optical computing
      ab: In the current issue of the Proceedings of the National Academy of Sciences, Dr. Thomas Serre describes how he and his colleagues at the Massachusetts Institute of Technology have built a computer that can recognize classes of things as accurately as a person can. Although computers are very good at solving specific problems, they have difficulty when it comes to working in a general way, for example in recognizing broad categories of images. However, Dr. Serre's computer, which is based on a model that closely imitates the functioning of the ventral visual pathway in the human brain, has proved the equal of human volunteers in distinguishing photographs containing animals from those without.
      pubtype: Periodical
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N