Empiricism without magic: transformational abstraction in deep convolutional neural networks.
In artificial intelligence, recent research has demonstrated the remarkable potential of Deep Convolutional Neural Networks (DCNNs), which seem to exceed state-of-the-art performance in new domains weekly, especially on the sorts of very difficult perceptual discrimination tasks that skeptics though...
| Publicado en: | Synthese Vol. 195; no. 12; pp. 5339 - 5373 |
|---|---|
| Autor principal: | |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Dec2018
|
| 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=133123726&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 133123726 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00397857 4LI jtl: Synthese issn: 00397857 maglogo: N pubinfo: dt: Dec2018 vid: 195 iid: 12 pid: 237 pub: Springer Nature artinfo: ui: 133123726 10.1007/s11229-018-01949-1 ppf: 5339 ppct: 34 formats: fmt: – @attributes: type: T – @attributes: type: P size: 2.9MB tig: atl: Empiricism without magic: transformational abstraction in deep convolutional neural networks. aug: au: Buckner, Cameron affil: Department of Philosophy, University of Houston, Agnes Arnold Hall, 3553 Cullen Boulevard Room 513, 77204-3004, Houston, TX, USA su: Connectionism Convolution codes Deep Learning (Book) Empiricism Abstraction reactions Biological neural networks sug: subj: Connectionism Convolution codes Deep Learning (Book) Empiricism Abstraction reactions Biological neural networks keyword: Abstraction Convolution Deep learning Mechanism Nuisance variation ab: In artificial intelligence, recent research has demonstrated the remarkable potential of Deep Convolutional Neural Networks (DCNNs), which seem to exceed state-of-the-art performance in new domains weekly, especially on the sorts of very difficult perceptual discrimination tasks that skeptics thought would remain beyond the reach of artificial intelligence. However, it has proven difficult to explain why DCNNs perform so well. In philosophy of mind, empiricists have long suggested that complex cognition is based on information derived from sensory experience, often appealing to a faculty of abstraction. Rationalists have frequently complained, however, that empiricists never adequately explained how this faculty of abstraction actually works. In this paper, I tie these two questions together, to the mutual benefit of both disciplines. I argue that the architectural features that distinguish DCNNs from earlier neural networks allow them to implement a form of hierarchical processing that I call “transformational abstraction”. Transformational abstraction iteratively converts sensory-based representations of category exemplars into new formats that are increasingly tolerant to “nuisance variation” in input. Reflecting upon the way that DCNNs leverage a combination of linear and non-linear processing to efficiently accomplish this feat allows us to understand how the brain is capable of bi-directional travel between exemplars and abstractions, addressing longstanding problems in empiricist philosophy of mind. I end by considering the prospects for future research on DCNNs, arguing that rather than simply implementing 80s connectionism with more brute-force computation, transformational abstraction counts as a qualitatively distinct form of processing ripe with philosophical and psychological significance, because it is significantly better suited to depict the generic mechanism responsible for this important kind of psychological processing in the brain. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Synthese is a copyright of Springer, 2018. All Rights Reserved. item: Synthese holder: Springer Nature dt: @attributes: year: 2018 holdings: @attributes: islocal: N |
|---|