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

A storage algorithm for two-layered neural networks

R Monasson

    International Journal of Neural Systems
    |June 1, 1994
    PubMed
    Summary
    This summary is machine-generated.

    A novel learning algorithm for two-layered committee machines converges in finite time. This efficient method outperforms exhaustive enumeration for internal representation analysis.

    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

    Emergence of Compositional Representations in Restricted Boltzmann Machines.

    Physical review letters·2017
    Same author

    Neural assemblies revealed by inferred connectivity-based models of prefrontal cortex recordings.

    Journal of computational neuroscience·2016
    Same author

    Transitions between Spatial Attractors in Place-Cell Models.

    Physical review letters·2015
    Same author

    Large pseudocounts and L2-norm penalties are necessary for the mean-field inference of Ising and Potts models.

    Physical review. E, Statistical, nonlinear, and soft matter physics·2014
    Same author

    Stochastic ratchet mechanisms for replacement of proteins bound to DNA.

    Physical review letters·2014
    Same author

    Crosstalk and transitions between multiple spatial maps in an attractor neural network model of the hippocampus: collective motion of the activity.

    Physical review. E, Statistical, nonlinear, and soft matter physics·2014

    Area of Science:

    • Machine Learning
    • Artificial Intelligence
    • Computational Neuroscience

    Background:

    • Committee machines are a class of neural networks.
    • Efficient learning algorithms are crucial for complex models.
    • Internal representations significantly impact model performance.

    Discussion:

    • The proposed algorithm offers a significant improvement over exhaustive methods.
    • Convergence guarantees provide reliability for practical applications.
    • The efficiency is demonstrated through comparative analysis.

    Key Insights:

    • A new, finite-time converging learning algorithm for two-layered committee machines is introduced.
    • The algorithm's efficiency is empirically validated against exhaustive enumeration.

    Related Experiment Videos

  • This work contributes to the development of more effective machine learning techniques.

    • Outlook:

    • Future research could explore extensions to deeper committee machine architectures.
    • Investigating the algorithm's scalability with larger datasets is warranted.
    • Potential applications in pattern recognition and data analysis can be explored.