Connectionism and the language of thought

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In an influential critique, Jerry Fodor and Zenon Pylyshyn point to the existence of a potentially devastating dilemma for connectionism (Fodor and Pylyshyn [1988]). Either connectionist models consist in mere associations of unstructured representations, or they consist in processes involving complex representations. If the former, connectionism is mere associationism, and will not be capable of accounting for very much of cognition. If the latter, then connectionist models concern only the implementation of cognitive processes, and are, therefore, not informative at the level of cognition. I shall argue that Fodor and Pylyshyn's argument is based on a crucial misunderstanding, the same misunderstanding which motivates the entire language of thought hypothesis.

Original languageEnglish (US)
Pages (from-to)485-503
Number of pages19
JournalBritish Journal for the Philosophy of Science
Volume45
Issue number2
DOIs
StatePublished - Jun 1994
Externally publishedYes

Fingerprint

Connectionism
cognition
Neural Networks (Computer)
Cognition
Language
Dilemma
Entire
Model
Language of Thought
Misunderstanding
Connectionist Models

ASJC Scopus subject areas

  • Molecular Biology
  • Statistics and Probability
  • Computational Mathematics
  • Condensed Matter Physics
  • History
  • History and Philosophy of Science
  • Philosophy

Cite this

Connectionism and the language of thought. / Rowlands, Mark.

In: British Journal for the Philosophy of Science, Vol. 45, No. 2, 06.1994, p. 485-503.

Research output: Contribution to journalArticle

@article{4ee7be7bcca34503921d78a7e326b5ee,
title = "Connectionism and the language of thought",
abstract = "In an influential critique, Jerry Fodor and Zenon Pylyshyn point to the existence of a potentially devastating dilemma for connectionism (Fodor and Pylyshyn [1988]). Either connectionist models consist in mere associations of unstructured representations, or they consist in processes involving complex representations. If the former, connectionism is mere associationism, and will not be capable of accounting for very much of cognition. If the latter, then connectionist models concern only the implementation of cognitive processes, and are, therefore, not informative at the level of cognition. I shall argue that Fodor and Pylyshyn's argument is based on a crucial misunderstanding, the same misunderstanding which motivates the entire language of thought hypothesis.",
author = "Mark Rowlands",
year = "1994",
month = "6",
doi = "10.1093/bjps/45.2.485",
language = "English (US)",
volume = "45",
pages = "485--503",
journal = "British Journal for the Philosophy of Science",
issn = "0007-0882",
publisher = "Oxford University Press",
number = "2",

}

TY - JOUR

T1 - Connectionism and the language of thought

AU - Rowlands, Mark

PY - 1994/6

Y1 - 1994/6

N2 - In an influential critique, Jerry Fodor and Zenon Pylyshyn point to the existence of a potentially devastating dilemma for connectionism (Fodor and Pylyshyn [1988]). Either connectionist models consist in mere associations of unstructured representations, or they consist in processes involving complex representations. If the former, connectionism is mere associationism, and will not be capable of accounting for very much of cognition. If the latter, then connectionist models concern only the implementation of cognitive processes, and are, therefore, not informative at the level of cognition. I shall argue that Fodor and Pylyshyn's argument is based on a crucial misunderstanding, the same misunderstanding which motivates the entire language of thought hypothesis.

AB - In an influential critique, Jerry Fodor and Zenon Pylyshyn point to the existence of a potentially devastating dilemma for connectionism (Fodor and Pylyshyn [1988]). Either connectionist models consist in mere associations of unstructured representations, or they consist in processes involving complex representations. If the former, connectionism is mere associationism, and will not be capable of accounting for very much of cognition. If the latter, then connectionist models concern only the implementation of cognitive processes, and are, therefore, not informative at the level of cognition. I shall argue that Fodor and Pylyshyn's argument is based on a crucial misunderstanding, the same misunderstanding which motivates the entire language of thought hypothesis.

UR - http://www.scopus.com/inward/record.url?scp=58349089683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58349089683&partnerID=8YFLogxK

U2 - 10.1093/bjps/45.2.485

DO - 10.1093/bjps/45.2.485

M3 - Article

VL - 45

SP - 485

EP - 503

JO - British Journal for the Philosophy of Science

JF - British Journal for the Philosophy of Science

SN - 0007-0882

IS - 2

ER -