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 Video

Updated: May 14, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Effects of supervised Self Organising Maps parameters on classification performance.

Davide Ballabio1, Mahdi Vasighi, Peter Filzmoser

  • 1Department of Environmental Sciences, University of Milano Bicocca, Milano, Italy. davide.ballabio@unimib.it

Analytica Chimica Acta
|February 16, 2013
PubMed
Summary

This study optimizes Self-Organizing Maps (SOMs) by analyzing key parameters affecting classification performance and computational time. Findings identify crucial settings and architectures for efficient neural network predictions.

Related Concept Videos

Survival Tree01:19

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a survival tree begins...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Untargeted <sup>1</sup>H NMR metabolomics to distinguish milk from different feeding systems for haymilk authentication.

Food research international (Ottawa, Ont.)·2026
Same author

Multivariate analysis of the label-declared nutritional composition of plant-based milk alternatives compared to milk in the Ecuadorian market.

Journal of the science of food and agriculture·2026
Same author

De novo design of anticancer 4-thiazolidinone derivatives: a generative framework shaped by activity cliffs.

Journal of cheminformatics·2026
Same author

Data Fusion Combining High-Resolution Mass Spectrometry and <sup>1</sup>H-NMR Metabolomic Data with Gluten Protein Content to Assess the Impact of Agro-Sustainable Treatments on Durum Wheat.

Molecules (Basel, Switzerland)·2026
Same author

Effects of feeding strategies on culture performance and product quality in NISTCHO.

NPJ systems biology and applications·2026
Same author

Machine Learning-Guided Design of Rhenium Tricarbonyl Complexes for Next-Generation Antibiotics.

ACS bio & med chem Au·2025

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Self-Organizing Maps (SOMs) are powerful neural network algorithms with adaptable parameters crucial for accurate predictions.
  • While some SOM parameter effects are known, others like initialization, topology, and boundary conditions remain less understood.
  • Network optimization for SOMs can be time-consuming, posing a significant disadvantage.

Purpose of the Study:

  • To comprehensively analyze the impact of various SOM parameters on classification performance.
  • To evaluate the influence of these parameters on computational times.
  • To identify optimal SOM settings and architectures for improved efficiency and accuracy.

Main Methods:

  • Utilized a design of experiments approach to contemporaneously evaluate multiple SOM parameters.

Related Experiment Videos

Last Updated: May 14, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

  • Tested a significant number of real datasets to ensure comprehensive statistical comparison.
  • Investigated interaction effects between different parameters.

    • Main Results:

    • Identified the most influential parameters affecting SOM classification performance.
    • Determined optimal parameter settings and network architectures.
    • Demonstrated methods to significantly reduce SOM computational time.

    Conclusions:

    • Parameter selection critically impacts SOM performance and efficiency.
    • The study provides a data-driven approach to optimize SOMs for specific applications.
    • Optimal configurations can lead to faster and more accurate neural network predictions.