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

Merging race models and adaptive networks: a parallel race network.

Denis Cousineau1

  • 1Université de Montréal, Montréal, Québec, Canada. denis.cousineau@umontreal.ca

Psychonomic Bulletin & Review
|March 1, 2005
PubMed
Summary

This study introduces a parallel race network, a novel computational model. This model learns stimulus-response associations and surprisingly solves the XOR problem without hidden units, demonstrating a new pathway for cognitive processing.

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

Error Cancellation During Early Task Performance.

Experimental psychology·2026
Same author

The Creative Space Theory as a map to explore the mind.

Possibility studies & society·2026
Same author

Do You See the Difference Between Perfection and Excellence?

Psychology research and behavior management·2026
Same author

The relation of spatial skills, spatial memory span, and two anxiety types with statistics anxiety in European and North American University students.

The British journal of educational psychology·2026
Same author

There are no alternative hypotheses in tests of null hypotheses.

Frontiers in psychology·2025
Same author

Unsupervised clustering reveals spatial and verbal cognitive profiles in aphantasia and typical imagery.

Neuropsychologia·2025

Area of Science:

  • Computational neuroscience
  • Cognitive modeling
  • Artificial intelligence

Background:

  • Traditional neural networks often rely on weighted sums.
  • Existing race models typically involve single channels.
  • Understanding complex cognitive processes requires flexible network architectures.

Purpose of the Study:

  • To introduce a generalized parallel race model with multiple channels.
  • To implement a learning rule for parallel race networks.
  • To demonstrate the model's ability to learn stimulus-response associations and solve complex problems.

Main Methods:

  • Development of a parallel race network architecture.
  • Implementation of a novel learning rule for the network.
  • Testing the network's performance on the XOR problem.

Related Experiment Videos

Main Results:

  • The parallel race network successfully learned stimulus-response associations.
  • A two-layer parallel race network solved the XOR problem without hidden units.
  • The model exhibited emergent seriality in responses despite its parallel nature.

Conclusions:

  • Parallel race networks offer a viable alternative to strength-based networks for cognitive processes.
  • The model demonstrates that complex learning can occur without hidden units.
  • The emergent seriality highlights the nuanced capabilities of parallel processing systems.