Deep convolutional neural networks are not mechanistic explanations of object recognition.
Given the extent of using deep convolutional neural networks to model the mechanism of object recognition, it becomes important to analyse the evidence of their similarity and the explanatory potential of these models. I focus on one frequent method of their comparison—representational similarity an...
| Publicado en: | Synthese Vol. 203; no. 1; pp. 1 - 29 |
|---|---|
| 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=174807289&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 174807289 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: 174807289 10.1007/s11229-023-04461-3 ppf: 1 ppct: 28 formats: fmt: – @attributes: type: T – @attributes: type: P size: 1.2MB tig: atl: Deep convolutional neural networks are not mechanistic explanations of object recognition. aug: au: Grujičić, Bojana affil: Max Planck School of Cognition, Leipzig, Germany https://ror.org/01hcx6992 Berlin School of Mind and Brain, Humboldt-Universität zu Berlin, Berlin, Germany https://ror.org/02jx3x895 Department of Science and Technology Studies, University College London, London, UK sug: keyword: Deep neural networks Explanation Mechanisms Object recognition Representation Similarity measures ab: Given the extent of using deep convolutional neural networks to model the mechanism of object recognition, it becomes important to analyse the evidence of their similarity and the explanatory potential of these models. I focus on one frequent method of their comparison—representational similarity analysis, and I argue, first, that it underdetermines these models as how-actually mechanistic explanations. This happens because different similarity measures in this framework pick out different mechanisms across DCNNs and the brain in order to correspond them, and there is no arbitration between them in terms of relevance for object recognition. Second, the reason similarity measures are underdetermining to a large degree stems from the highly idealised nature of these models, which undermines their status as how-possibly mechanistic explanatory models of object recognition as well. Thus, building models with more theoretical consideration and choosing relevant similarity measures may bring us closer to the goal of mechanistic explanation. 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 |
|---|