The deep neural network approach to the reference class problem.

Methods of machine learning (ML) are gradually complementing and sometimes even replacing methods of classical statistics in science. This raises the question whether ML faces the same methodological problems as classical statistics. This paper sheds light on this question by investigating a long-st...

Descripción completa

Detalles Bibliográficos
Publicado en:Synthese Vol. 201; no. 3; pp. 1 - 25
Autor principal: Buchholz, Oliver
Formato: Artículo
Publicado: Springer Nature Mar2023
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=162490163&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 162490163
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00397857
        4LI
      jtl: Synthese
      issn: 00397857
      maglogo: N
    pubinfo:
      dt: Mar2023
      vid: 201
      iid: 3
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        162490163
        10.1007/s11229-023-04110-9
      ppf: 1
      ppct: 24
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 557KB
      tig:
        atl: The deep neural network approach to the reference class problem.
      aug:
        au: Buchholz, Oliver
        affil: University of Tübingen, Cluster of Excellence “Machine Learning: New Perspectives for Science”, Maria-von-Linden-Str. 6, 72076, Tübingen, Germany
      sug:
      keyword:
        Big data
        Deep neural networks
        Machine learning
        Overfitting
        Prediction
        Reference class problem
      ab: Methods of machine learning (ML) are gradually complementing and sometimes even replacing methods of classical statistics in science. This raises the question whether ML faces the same methodological problems as classical statistics. This paper sheds light on this question by investigating a long-standing challenge to classical statistics: the reference class problem (RCP). It arises whenever statistical evidence is applied to an individual object, since the individual belongs to several reference classes and evidence might vary across them. Thus, the problem consists in choosing a suitable reference class for the individual. I argue that deep neural networks (DNNs) are able to overcome specific instantiations of the RCP. Whereas the criteria of narrowness, reliability, and homogeneity, that have been proposed to determine a suitable reference class, pose an inextricable tradeoff to classical statistics, DNNs are able to satisfy them in some situations. On the one hand, they can exploit the high dimensionality in big-data settings. I argue that this corresponds to the criteria of narrowness and reliability. On the other hand, ML research indicates that DNNs are generally not susceptible to overfitting. I argue that this property is related to a particular form of homogeneity. Taking both aspects together reveals that there are specific settings in which DNNs can overcome the RCP.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Synthese is a copyright of Springer, 2023. All Rights Reserved.
      item: Synthese
      holder: Springer Nature
      dt:
        @attributes:
          year: 2023
    holdings:
      @attributes:
        islocal: N