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

Equivalence between RAM-based neural networks and probabilistic automata.

Marcilio C P de Souto, Teresa B Ludermir, Wilson R de Oliveira

    IEEE Transactions on Neural Networks
    |August 27, 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 author

    Topological analysis of the three-dimensional radiodensity distribution of fish otoliths: Point sampling effects on dimensionality reduction.

    Micron (Oxford, England : 1993)·2024
    Same author

    Combining STDP and binary networks for reinforcement learning from images and sparse rewards.

    Neural networks : the official journal of the International Neural Network Society·2021
    Same author

    Quantum neuron with real weights.

    Neural networks : the official journal of the International Neural Network Society·2021
    Same author

    Implementing Any Nonlinear Quantum Neuron.

    IEEE transactions on neural networks and learning systems·2019
    Same author

    Impact of missing data imputation methods on gene expression clustering and classification.

    BMC bioinformatics·2015
    Same author

    Guest editorial for special section on BSB 2012.

    IEEE/ACM transactions on computational biology and bioinformatics·2014

    This study analyzes the computational power of general single-layer sequential weightless neural networks (GSSWNNs), which are RAM-based. The findings enhance understanding of their temporal dynamics and may inform new learning algorithm development.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Computational Neuroscience

    Background:

    • Random access memory (RAM)-based neural networks offer unique computational properties.
    • General single-layer sequential weightless neural networks (GSSWNNs) represent a specific class of these architectures.

    Purpose of the Study:

    • To analyze the computational power of GSSWNNs.
    • To deepen the understanding of the temporal behavior of these neural networks.
    • To provide insights for the development of novel learning algorithms.

    Main Methods:

    • Theoretical analysis of GSSWNN computational capabilities.
    • Examination of the temporal dynamics inherent in the network structure.

    Main Results:

    Related Experiment Videos

    • Characterization of the computational power of GSSWNNs.
    • Identification of key factors influencing their temporal behavior.

    Conclusions:

    • The theoretical results contribute to a better understanding of GSSWNNs.
    • Insights gained could guide the creation of new machine learning algorithms.