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 self-organizing map for adaptive processing of structured data.

M Hagenbuchner1, A Sperduti, Ah Chung Tsoi

  • 1Fac. of Informatics, Univ. of Wollongong, NSW, Australia.

IEEE Transactions on Neural Networks
|February 2, 2008
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

Point cloud dosimetry framework for preclinical microbeam radiation therapy.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2025
Same author

Comparison of Deep Learning Models for fast and accurate dose map prediction in Microbeam Radiation Therapy.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2025
Same author

Dual-Branch Multi-Dimensional Attention Mechanism for Joint Facial Expression Detection and Classification.

Sensors (Basel, Switzerland)·2025
Same author

An Innovative Neighbor Attention Mechanism Based on Coordinates for the Recognition of Facial Expressions.

Sensors (Basel, Switzerland)·2024
Same author

Facial Expression Recognition-You Only Look Once-Neighborhood Coordinate Attention Mamba: Facial Expression Detection and Classification Based on Neighbor and Coordinates Attention Mechanism.

Sensors (Basel, Switzerland)·2024
Same author

Accurate and Fast Deep Learning Dose Prediction for a Preclinical Microbeam Radiation Therapy Study Using Low-Statistics Monte Carlo Simulations.

Cancers·2023
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

We introduce a novel unsupervised neural network model, an extension of self-organizing maps (SOMs), for analyzing labeled directed acyclic graphs (DAGs). This model effectively uncovers similarities within complex data by utilizing both node labels and graph topology.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Neural networks have advanced, enabling structured data processing.
  • Existing models often require supervision for complex data analysis.
  • Analyzing labeled directed acyclic graphs (DAGs) presents unique challenges.

Purpose of the Study:

  • To propose the first fully unsupervised neural network model for processing labeled DAGs.
  • To extend traditional self-organizing maps (SOMs) for enhanced structured data analysis.
  • To discover similarities in objects represented as labeled DAGs.

Main Methods:

  • An extension of self-organizing maps (SOMs) was developed.
  • The unfolding procedure from recurrent and recursive neural networks was employed.

Related Experiment Videos

  • Replicated neurons in the unfolded network formed a complete SOM.

    • Main Results:

    • The model successfully processes labeled directed acyclic graphs (DAGs).
    • It discovers similarities among objects, including numerical data vectors.
    • Experimental analysis on a benchmark dataset confirmed model capabilities.

    Conclusions:

    • The proposed unsupervised SOM extension effectively processes labeled DAGs.
    • The model leverages both node label information and DAG topology.
    • This represents a significant advancement in unsupervised learning for structured data.