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

Neural computation by concentrating information in time.

D W Tank, J J Hopfield

    Proceedings of the National Academy of Sciences of the United States of America
    |April 1, 1987
    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 synthesis-diffusion-degradation model explains Bicoid gradient formation in unfertilized eggs.

    Physical biology·2012
    Same author

    Searching for memories, Sudoku, implicit check bits, and the iterative use of not-always-correct rapid neural computation.

    Neural computation·2008
    Same author

    Encoding for computation: recognizing brief dynamical patterns by exploiting effects of weak rhythms on action-potential timing.

    Proceedings of the National Academy of Sciences of the United States of America·2004
    Same author

    Spontaneous eye movements in goldfish: oculomotor integrator performance, plasticity, and dependence on visual feedback.

    Vision research·2004
    Same author

    Learning rules and network repair in spike-timing-based computation networks.

    Proceedings of the National Academy of Sciences of the United States of America·2003
    Same author

    Simple networks for spike-timing-based computation, with application to olfactory processing.

    Neuron·2003
    Same journal

    In This Issue.

    Proceedings of the National Academy of Sciences of the United States of America·2026
    Same journal

    Long-term cultural continuity across the Neanderthal-modern human sequence at Üçağızlı II Cave, northern Levant.

    Proceedings of the National Academy of Sciences of the United States of America·2026
    Same journal

    Dolphins use names to remember whom to avoid.

    Proceedings of the National Academy of Sciences of the United States of America·2026
    Same journal

    Retraction for Shaked and Frenkel, Curiouser and curiouser: Meningeal lymphoid structures in the aging brain.

    Proceedings of the National Academy of Sciences of the United States of America·2026
    Same journal

    Small but mighty: The outsized role of small water bodies in the global carbon cycle.

    Proceedings of the National Academy of Sciences of the United States of America·2026
    Same journal

    Functional traits produce conditional outcomes in different community contexts.

    Proceedings of the National Academy of Sciences of the United States of America·2026
    See all related articles

    This study introduces an analog neural network model for recognizing patterns in time-dependent signals. The network utilizes patterned delays to process sequential information, demonstrating capabilities in speech recognition tasks.

    Area of Science:

    • Computational neuroscience
    • Artificial intelligence
    • Signal processing

    Background:

    • Recognizing patterns in time-dependent signals is crucial for tasks like speech processing.
    • Existing models may face challenges in efficiently handling sequential information.

    Purpose of the Study:

    • To present an analog model neural network capable of general pattern recognition in time-dependent signals.
    • To demonstrate its application in tasks analogous to continuous speech recognition.

    Main Methods:

    • The proposed network employs a patterned set of delays to focus stimulus sequence information.
    • The network's computational principles are explained through an energy minimization framework.
    • Neurobiological mechanisms for generating necessary delays are known.

    Related Experiment Videos

    Main Results:

    • The analog neural network successfully processes time-dependent signals.
    • Demonstrated computational capabilities in tasks similar to word recognition in continuous speech.
    • The network architecture is linked to an energy function minimization process.

    Conclusions:

    • The developed analog neural network offers a novel approach for sequential pattern recognition.
    • The model's architecture and function are grounded in principles of energy minimization.
    • The approach is potentially applicable to complex real-world signal processing challenges.