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 high-order graph generating self-organizing structure.

Riccardo Rizzo1

  • 1Institute of High Performance Computing and Networking, Italian National Research Council, viale delle Scienze, Ed. 11 Palermo, 90128, Italy. ricrizzo@pa.icar.cnr.it

International Journal of Neural Systems
|November 10, 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

TUSC3 serves as a rate-limiting gatekeeper of a glycan-mediated ER triage checkpoint for BMP4/Dpp.

Cell reports·2026
Same author

Overprinting with tomographic volumetric additive manufacturing.

Nature communications·2026
Same author

High-efficiency multi-scale holographic volumetric 3D printing with a phase light modulator.

Light, science & applications·2026
Same author

Mining cancer genomes for copy number alterations identifies glycosylation enzymes as oncogenic drivers.

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

Intra-diaphragmatic extralobar pulmonary sequestration: Surgical approaches and outcome.

Journal of pediatric surgery·2025
Same author

TUSC3 serves as a rate-limiting gatekeeper of a glycan-mediated ER Triage Checkpoint for BMP4/Dpp.

bioRxiv : the preprint server for biology·2025
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study presents a novel structure for extracting high-order information from self-organizing neural networks. The algorithm creates a two-layer hierarchical structure, simplifying complex network maps for better data analysis.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Neural networks often use fixed or learned lattice topologies.
  • These networks serve as neighborhood-preserving maps of input data manifolds.
  • Managing these complex graph structures with numerous nodes is challenging.

Purpose of the Study:

  • To develop a general structure for extracting high-order information from self-organizing neural network graphs.
  • To enable the creation of hierarchical representations for complex network data.
  • To facilitate topology-preserving mapping when input data allows.

Main Methods:

  • A general structure is proposed to process graphs generated by self-organizing networks.
  • The algorithm constructs a two-layer hierarchical structure.

Related Experiment Videos

  • It leverages neural networks suitable for input data distribution.

    • Main Results:

    • The proposed structure effectively extracts high-order information from network graphs.
    • A two-layer hierarchical structure is successfully built from the network outputs.
    • The algorithm demonstrates capability in topology-preserving mapping.

    Conclusions:

    • The developed structure offers a method for abstracting and managing complex neural network topologies.
    • It provides a scalable approach to analyzing high-dimensional data represented by neural maps.
    • This hierarchical approach enhances the utility of self-organizing networks in data representation and analysis.