Jove
Visualize
Contact Us

Related Experiment Videos

Refractory pulse counting processes in stochastic neural computers.

Dean K McNeill, Howard C Card

    IEEE Transactions on Neural Networks
    |March 25, 2005
    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 journal

    Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

    IEEE transactions on neural networks·2013
    Same journal

    Guest editorial: special section on white box nonlinear prediction models.

    IEEE transactions on neural networks·2011
    Same journal

    Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

    IEEE transactions on neural networks·2011
    Same journal

    Guest editorial: special section on data-based control, modeling, and optimization.

    IEEE transactions on neural networks·2011
    Same journal

    Neural network-based multiple robot simultaneous localization and mapping.

    IEEE transactions on neural networks·2011
    Same journal

    Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

    IEEE transactions on neural networks·2011
    See all related articles
    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

    A temporary dead time in stochastic Bernoulli processors significantly reduces pulse recording accuracy. This effect, crucial for neural networks, increases with dead time and system probability, impacting mean and variance.

    Area of Science:

    • Computational neuroscience
    • Stochastic processes
    • Information theory

    Background:

    • Investigates the impact of temporary refractory periods (dead time) on stochastic Bernoulli processors.
    • Examines how dead time affects the recording of subsequent pulse events after an initial pulse arrival.

    Discussion:

    • Analyzes the transient period during which the system reaches equilibrium, noting its dependence on dead time and Bernoulli probability.
    • Discusses implications for stochastic neural networks and subsequent data processing stages.

    Key Insights:

    • Dead time significantly reduces the mean and variance of pulse count distributions.
    • This reduction is substantial unless the Bernoulli probability is small relative to the inverse of the dead time.

    Related Experiment Videos

    Outlook:

    • Highlights the importance of accounting for dead time in designing and analyzing stochastic systems.
    • Suggests further research into optimizing processor parameters to mitigate dead time effects in neural network applications.