Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

How do connectionist networks compute?

Gerard O'Brien1, Jon Opie

  • 1Discipline of Philosophy, University of Adelaide, 5005, Adelaide, SA, Australia. gerard.obrien@adelaide.edu.au

Cognitive Processing
|April 22, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The role of representation in computation.

Cognitive processing·2008
Same author

Vehicle, process, and hybrid theories of consciousness.

The Behavioral and brain sciences·2008
Same author

Treatment of unilateral visual impairment on preschool vision screening: preschool vision screening should continue, perhaps earlier.

BMJ (Clinical research ed.)·2004
Same author

Obesity and the risk of heart failure.

The New England journal of medicine·2002
Same author

Interns' perceptions of performance and confidence in participating in and managing simulated and real cardiac arrest situations.

Medical teacher·2002
Same journal

The STEARC effect revisited: does time shape spatial attention and memory?

Cognitive processing·2026
Same journal

Higher- and lower-level processing in strategic reading: Reconceptualising the Survey of Reading Strategies (SORS).

Cognitive processing·2026
Same journal

More caution or more lenient: deciphering the role of negative affect in recognition and inference.

Cognitive processing·2026
Same journal

Cognitive offloading, critical thinking and attitudes towards artificial intelligence in the era of ChatGPT: a comparative study of artificial intelligence-assisted and manual task performance in young adults.

Cognitive processing·2026
Same journal

Emojis vs. black-and-white and colored drawings: comparing living and non-living things in oral naming.

Cognitive processing·2026
Same journal

The impact of facial expressions on space- and object-based attention by gaze cues.

Cognitive processing·2026
See all related articles

This study clarifies how connectionist networks compute, addressing doubts about their computational nature. It establishes a robust framework for understanding connectionist computation through representational capacities of connection weights.

Area of Science:

  • Cognitive Science
  • Computational Neuroscience
  • Philosophy of Mind

Background:

  • Connectionism is proposed as an alternative to classical computational theories of mind.
  • Doubts exist regarding the computational validity of connectionist networks.
  • A canonical definition of computation in cognitive science remains elusive.

Purpose of the Study:

  • To demonstrate that connectionist networks possess genuine computational capabilities.
  • To develop a comprehensive account of computation within connectionist models.
  • To address and dispel persistent doubts about connectionism's computational credentials.

Main Methods:

  • Developing a generic, explanatorily relevant account of computation.
  • Analyzing the conventional understanding of connectionist computation and its limitations.

Related Experiment Videos

  • Proposing a new framework for connectionist computation based on representational capacities of connection weights.

    • Main Results:

    • The conventional account of connectionist computation is shown to be inadequate.
    • A novel framework for understanding connectionist computation is developed.
    • The representational capacities of connection weights are explained and analyzed.

    Conclusions:

    • Connectionist networks are demonstrably computational.
    • A robust understanding of connectionist computation is achieved through analyzing connection weights.
    • This work provides a foundation for reconciling connectionism with computational theories of mind.