Throwing light on black boxes: emergence of visual categories from deep learning.

One of the best known arguments against the connectionist approach to artificial intelligence and cognitive science is that neural networks are black boxes, i.e., there is no understandable account of their operation. This difficulty has impeded efforts to explain how categories arise from raw senso...

Full description

Bibliographic Details
Published in:Synthese Vol. 198; no. 10; pp. 10021 - 10042
Main Author: López-Rubio, Ezequiel
Format: Article
Published: Springer Nature Oct2021
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=152559386&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 152559386
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00397857
        4LI
      jtl: Synthese
      issn: 00397857
      maglogo: N
    pubinfo:
      dt: Oct2021
      vid: 198
      iid: 10
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        152559386
        10.1007/s11229-020-02700-5
      ppf: 10021
      ppct: 21
      formats:
        fmt:
          @attributes:
            type: P
            size: 428KB
      tig:
        atl: Throwing light on black boxes: emergence of visual categories from deep learning.
      aug:
        au: López-Rubio, Ezequiel
        affil:
          Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga (UMA), Bulevar Louis Pasteur 35, 29071, Málaga, Spain
          Departamento de Lógica, Historia y Filosofía de la Ciencia, Universidad Nacional de Educación a Distancia (UNED), Paseo de Senda del Rey 7, 28040, Madrid, Spain
      su:
        Artificial intelligence
        Deep learning
        Generative adversarial networks
        Convolutional neural networks
        Cognitive science
        Cognition
      sug:
        subj:
          Artificial intelligence
          Deep learning
          Generative adversarial networks
          Convolutional neural networks
          Cognitive science
          Cognition
      keyword:
        Machine learning
        Visual categories
      ab: One of the best known arguments against the connectionist approach to artificial intelligence and cognitive science is that neural networks are black boxes, i.e., there is no understandable account of their operation. This difficulty has impeded efforts to explain how categories arise from raw sensory data. Moreover, it has complicated investigation about the role of symbols and language in cognition. This state of things has been radically changed by recent experimental findings in artificial deep learning research. Two kinds of artificial deep learning networks, namely the convolutional neural network and the generative adversarial network have been found to possess the capability to build internal states that are interpreted by humans as complex visual categories, without any specific hints or any grammatical processing. This emergent ability suggests that those categories do not depend on human knowledge or the syntactic structure of language, while they do rely on their visual context. This supports a mild form of empiricism, while it does not assume that computational functionalism is true. Some consequences are extracted regarding the debate about amodal and grounded representations in the human brain. Furthermore, new avenues for research on cognitive science are open.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Synthese is a copyright of Springer, 2021. All Rights Reserved.
      item: Synthese
      holder: Springer Nature
      dt:
        @attributes:
          year: 2021
    holdings:
      @attributes:
        islocal: N