EXPLAINING WITH REASONS: FROM ARISTOTLE TO MACHINE LEARNING CLASSIFIERS.
Explanations, and in particular explanations which provide the reasons why their conclusion is true, are a central object in a range of fields. On the one hand, there is a long and illustrious philosophical tradition, which starts from Aristotle, and passes through scholars such as Leibniz, Bolzano...
| Publicado en: | Review of Symbolic Logic Vol. 18; no. 4; pp. 1068 - 1090 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
Cambridge University Press
Dec2025
|
| 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=190692237&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 190692237 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 17550203 8OI1 jtl: Review of Symbolic Logic issn: 17550203 maglogo: N pubinfo: dt: Dec2025 vid: 18 iid: 4 pid: 15979 pub: Cambridge University Press artinfo: ui: 190692237 10.1017/S1755020325100786 ppf: 1068 ppct: 22 formats: tig: atl: EXPLAINING WITH REASONS: FROM ARISTOTLE TO MACHINE LEARNING CLASSIFIERS. aug: au: HILL, BRIAN POGGIOLESI, FRANCESCA affil: CNRS & HEC PARIS GREGHEC JOUY-EN-JOSAS 78350 FRANCE E-mail IHPST UMR 8590 CNRS UNIVERSITÉ PARIS 1 PANTHÉON-SORBONNE su: Machine learning Proof theory Classification algorithms Philosophers Ancient philosophy Aristotle, 384-322 B.C. Rationalism Explanation sug: subj: Machine learning Proof theory Classification algorithms Philosophers Ancient philosophy Aristotle, 384-322 B.C. Rationalism Explanation keyword: explanation machine learning classifiers reasons sequent calculus ab: Explanations, and in particular explanations which provide the reasons why their conclusion is true, are a central object in a range of fields. On the one hand, there is a long and illustrious philosophical tradition, which starts from Aristotle, and passes through scholars such as Leibniz, Bolzano and Frege, that give pride of place to this type of explanation, and is rich with brilliant and profound intuitions. Recently, Poggiolesi [25] has formalized ideas coming from this tradition using logical tools of proof theory. On the other hand, recent work has focused on Boolean circuits that compile some common machine learning classifiers and have the same input-output behavior. In this framework, Darwiche and Hirth [7] have proposed a theory for unveiling the reasons behind the decisions made by Boolean classifiers, and they have studied their theoretical implications. In this paper, we uncover the deep links behind these two trends, demonstrating that the proof-theoretic tools introduced by Poggiolesi provide reasons for decisions, in the sense of Darwiche and Hirth [7]. We discuss the conceptual as well as the technical significance of this result. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|