Conceptual challenges for interpretable machine learning.

As machine learning has gradually entered into ever more sectors of public and private life, there has been a growing demand for algorithmic explainability. How can we make the predictions of complex statistical models more intelligible to end users? A subdiscipline of computer science known as inte...

Descripción completa

Detalles Bibliográficos
Publicado en:Synthese Vol. 200; no. 1; pp. 1 - 17
Autor principal: Watson, David S.
Formato: Artículo
Publicado: Springer Nature Feb2022
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=155641237&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 155641237
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00397857
        4LI
      jtl: Synthese
      issn: 00397857
      maglogo: N
    pubinfo:
      dt: Feb2022
      vid: 200
      iid: 1
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        155641237
        10.1007/s11229-022-03485-5
      ppf: 1
      ppct: 16
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 774KB
      tig:
        atl: Conceptual challenges for interpretable machine learning.
      aug:
        au: Watson, David S.
        affil: University College London, London, UK
      sug:
      keyword:
        Artificial intelligence
        Causality
        Explainability
        Scientific explanation
        Severe testing
      ab: As machine learning has gradually entered into ever more sectors of public and private life, there has been a growing demand for algorithmic explainability. How can we make the predictions of complex statistical models more intelligible to end users? A subdiscipline of computer science known as interpretable machine learning (IML) has emerged to address this urgent question. Numerous influential methods have been proposed, from local linear approximations to rule lists and counterfactuals. In this article, I highlight three conceptual challenges that are largely overlooked by authors in this area. I argue that the vast majority of IML algorithms are plagued by (1) ambiguity with respect to their true target; (2) a disregard for error rates and severe testing; and (3) an emphasis on product over process. Each point is developed at length, drawing on relevant debates in epistemology and philosophy of science. Examples and counterexamples from IML are considered, demonstrating how failure to acknowledge these problems can result in counterintuitive and potentially misleading explanations. Without greater care for the conceptual foundations of IML, future work in this area is doomed to repeat the same mistakes.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Synthese is a copyright of Springer, 2022. All Rights Reserved.
      item: Synthese
      holder: Springer Nature
      dt:
        @attributes:
          year: 2022
    holdings:
      @attributes:
        islocal: N