The Importance of Understanding Deep Learning.

Some machine learning models, in particular deep neural networks (DNNs), are not very well understood; nevertheless, they are frequently used in science. Does this lack of understanding pose a problem for using DNNs to understand empirical phenomena? Emily Sullivan has recently argued that understan...

Descripción completa

Detalles Bibliográficos
Publicado en:Erkenntnis Vol. 89; no. 5; pp. 1823 - 1841
Autores principales: Räz, Tim, Beisbart, Claus
Formato: Artículo
Publicado: Springer Nature Jun2024
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=177192671&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 177192671
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        01650106
        5KZ
      jtl: Erkenntnis
      issn: 01650106
      maglogo: N
    pubinfo:
      dt: Jun2024
      vid: 89
      iid: 5
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        177192671
        10.1007/s10670-022-00605-y
      ppf: 1823
      ppct: 18
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 794KB
      tig:
        atl: The Importance of Understanding Deep Learning.
      aug:
        au:
          Räz, Tim
          Beisbart, Claus
        affil:
          https://ror.org/02k7v4d05 University of Bern, Institute of Philosophy, Länggassstrasse 49a, 3012, Bern, Switzerland
          https://ror.org/02k7v4d05 Center for Artificial Intelligence in Medicine, University of Bern, Bern, Switzerland
      su:
        Artificial neural networks
        Deep learning
        Machine learning
      sug:
        subj:
          Artificial neural networks
          Deep learning
          Machine learning
      ab: Some machine learning models, in particular deep neural networks (DNNs), are not very well understood; nevertheless, they are frequently used in science. Does this lack of understanding pose a problem for using DNNs to understand empirical phenomena? Emily Sullivan has recently argued that understanding with DNNs is not limited by our lack of understanding of DNNs themselves. In the present paper, we will argue, contra Sullivan, that our current lack of understanding of DNNs does limit our ability to understand with DNNs. Sullivan's claim hinges on which notion of understanding is at play. If we employ a weak notion of understanding, then her claim is tenable, but rather weak. If, however, we employ a strong notion of understanding, particularly explanatory understanding, then her claim is not tenable.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Erkenntnis is a copyright of Springer, 2024. All Rights Reserved.
      item: Erkenntnis
      holder: Springer Nature
      dt:
        @attributes:
          year: 2024
    holdings:
      @attributes:
        islocal: N