Functional Concept Proxies and the Actually Smart Hans Problem: What’s Special About Deep Neural Networks in Science.
Deep Neural Networks (DNNs) are becoming increasingly important as scientific tools, as they excel in various scientific applications beyond what was considered possible. Yet from a certain vantage point, they are nothing but parametrized functions f θ (x) of some data vector x , and their ‘learning...
| Publicado en: | Synthese Vol. 203; no. 1; pp. 1 - 40 |
|---|---|
| Autor principal: | |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Jan2024
|
| 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=174479158&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 174479158 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00397857 4LI jtl: Synthese issn: 00397857 maglogo: N pubinfo: dt: Jan2024 vid: 203 iid: 1 pid: 237 pub: Springer Nature artinfo: ui: 174479158 10.1007/s11229-023-04440-8 ppf: 1 ppct: 39 formats: fmt: – @attributes: type: T – @attributes: type: P size: 2.1MB tig: atl: Functional Concept Proxies and the Actually Smart Hans Problem: What’s Special About Deep Neural Networks in Science. aug: au: Boge, Florian J. affil: https://ror.org/00613ak93 Interdisciplinary Centre for Science and Technology Studies (IZWT), Wuppertal University, Wuppertal, Germany Institute for Philosophy and Political Science (IPP), TU Dortmund, Emil-Figge-Str. 50, room 2.247, 44227, Dortmund, Germany sug: keyword: Automated science Clever Hans Problem Concepts Deep Neural Networks Reasoning ab: Deep Neural Networks (DNNs) are becoming increasingly important as scientific tools, as they excel in various scientific applications beyond what was considered possible. Yet from a certain vantage point, they are nothing but parametrized functions f θ (x) of some data vector x , and their ‘learning’ is nothing but an iterative, algorithmic fitting of the parameters to data. Hence, what could be special about them as a scientific tool or model? I will here suggest an integrated perspective that mediates between extremes, by arguing that what makes DNNs in science special is their ability to develop functional concept proxies (FCPs): Substructures that occasionally provide them with abilities that correspond to those facilitated by concepts in human reasoning. Furthermore, I will argue that this introduces a problem that has so far barely been recognized by practitioners and philosophers alike: That DNNs may succeed on some vast and unwieldy data sets because they develop FCPs for features that are not transparent to human researchers. The resulting breach between scientific success and human understanding I call the ‘Actually Smart Hans Problem’. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Synthese is a copyright of Springer, 2024. All Rights Reserved. item: Synthese holder: Springer Nature dt: @attributes: year: 2024 holdings: @attributes: islocal: N |
|---|