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

Learning by statistical cooperation of self-interested neuron-like computing elements.

A G Barto

    Human Neurobiology
    |January 1, 1985
    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

    Distributed representation of limb motor programs in arrays of adjustable pattern generators.

    Journal of cognitive neuroscience·2013
    Same author

    A cerebellar model of timing and prediction in the control of reaching.

    Neural computation·1999
    Same author

    Prediction of complex two-dimensional trajectories by a cerebellar model of smooth pursuit eye movement.

    Journal of neurophysiology·1997
    Same author

    Reinforcement learning control.

    Current opinion in neurobiology·1994
    Same author

    Distributed motor commands in the limb premotor network.

    Trends in neurosciences·1993
    Same author

    Linear systems analysis of the relationship between firing of deep cerebellar neurons and the classically conditioned nictitating membrane response in rabbits.

    Biological cybernetics·1991

    This study introduces self-interested adaptive elements that learn to cooperate for mutual benefit. This novel approach to cooperative computation may solve complex learning problems in artificial and biological networks.

    Area of Science:

    • Computational neuroscience
    • Artificial intelligence
    • Game theory

    Background:

    • Traditional cooperative computation models lack agent self-interest, limiting connections to game theory.
    • Existing models do not account for component preferences in network interactions.

    Purpose of the Study:

    • To introduce a novel approach to cooperative computation using self-interested adaptive elements.
    • To demonstrate how these elements can learn to cooperate to achieve individual and collective goals.
    • To explore the application of game theory concepts to computational networks.

    Main Methods:

    • Development of a robust adaptive element capable of learning and cooperation.
    • Computer simulations to test the learning capabilities of networks composed of these elements.

    Related Experiment Videos

  • Comparative analysis with existing algorithms and theoretical frameworks.

    • Main Results:

    • Networks of self-interested adaptive elements successfully solved complex learning problems.
    • Demonstrated the potential for robust adaptive elements to learn cooperation.
    • Validated the effectiveness of the proposed computational model.

    Conclusions:

    • Cooperative computation can be advanced by incorporating self-interested agents.
    • Game theory principles offer valuable insights for designing adaptive computational systems.
    • This approach holds promise for addressing challenges in both biological and artificial neural networks.