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

Generalizing self-organizing map for categorical data.

Chung-Chian Hsu1

  • 1Department of Information Management, National Yunlin University of Science and Technology, Yunlin 640, Taiwan. hsucc@yuntech.edu.tw

IEEE Transactions on Neural Networks
|March 29, 2006
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

Novel deep learning solutions with layered recurrent neural networks for nonlinear stiff Dahl hysteresis model in piezoelectric actuator.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Forecasting PM 2.5 concentration based on integrating of CEEMDAN decomposition method with SVM and LSTM.

Ecotoxicology and environmental safety·2023
Same author

A robust approach for endotracheal tube localization in chest radiographs.

Frontiers in artificial intelligence·2023
Same author

Explainable analytics: understanding causes, correcting errors, and achieving increasingly perfect accuracy from the nature of distinguishable patterns.

Scientific reports·2022
Same author

Visualized analysis of mixed numeric and categorical data via extended self-organizing map.

IEEE transactions on neural networks and learning systems·2014
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

This study introduces a generalized self-organizing map (SOM) that directly processes categorical data. This new model preserves similarity information, improving topological order representation in data visualization.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Data Mining

Background:

  • Self-organizing maps (SOMs) are unsupervised neural networks for high-dimensional data projection.
  • Conventional SOMs primarily handle numeric data, often losing categorical data's inherent similarity during conversion.
  • This limitation hinders accurate topological order representation in SOM applications.

Purpose of the Study:

  • To propose a generalized self-organizing map (SOM) model capable of directly processing categorical data.
  • To introduce a method for specifying similarity between categorical values using distance hierarchies.
  • To unify distance computation for both numeric and categorical data within the SOM framework.

Main Methods:

  • Developed a generalized SOM model incorporating distance hierarchies.

Related Experiment Videos

  • Implemented a method to map both numeric and categorical values to distance hierarchies.
  • Measured distances within these hierarchies to unify computations.
  • Trained and evaluated the model on synthetic and real-world datasets.

    • Main Results:

    • The generalized SOM model effectively processes categorical data directly.
    • Distance hierarchies preserve and utilize similarity information between categorical values.
    • The unified distance computation approach enhances SOM performance.
    • Experimental results confirm the model's effectiveness in reflecting accurate topological order.

    Conclusions:

    • The proposed generalized SOM model overcomes limitations of conventional SOMs with categorical data.
    • Distance hierarchies provide an intuitive and effective mechanism for handling categorical data similarity.
    • This advancement enables more accurate data visualization and analysis across diverse domains.