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

The time-organized map algorithm: extending the self-organizing map to spatiotemporal signals.

Jan C Wiemer1

  • 1Institut für Neuroinformatik, Ruhr-Universität Bochum, Germany. j.wiemer@dkfz.de

Neural Computation
|June 14, 2003
PubMed
Summary

The new time-organized map (TOM) algorithm enhances self-organizing maps (SOMs) to process spatiotemporal signals. It reveals how neural networks embed temporal context into spatial representations, explaining cortical organization.

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

Machine learning to optimize the diagnostic performance of natriuretic peptides for acute heart failure across age groups.

ESC heart failure·2026
Same author

Machine learning to optimize use of natriuretic peptides in the diagnosis of acute heart failure.

European heart journal. Acute cardiovascular care·2025
Same author

Performance evaluation of a new prognostic-efficacy-combination design in the context of telemedical interventions.

ESC heart failure·2022
Same author

Development and validation of a decision support tool for the diagnosis of acute heart failure: systematic review, meta-analysis, and modelling study.

BMJ (Clinical research ed.)·2022
Same author

Improve Management of acute heart failure with ProcAlCiTonin in EUrope: results of the randomized clinical trial IMPACT EU Biomarkers in Cardiology (BIC) 18.

European journal of heart failure·2019
Same author

Multicentre cross-sectional observational registry to monitor the safety of early discharge after rule-out of acute myocardial infarction by copeptin and troponin: the Pro-Core registry.

BMJ open·2019

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Cognitive Science

Background:

  • Traditional self-organizing maps (SOMs) excel at processing spatial data.
  • Understanding the self-organization and geometric structure of cortical signal representations is crucial.
  • Existing models often struggle to incorporate the temporal dynamics inherent in biological signals.

Purpose of the Study:

  • To introduce a novel time-organized map (TOM) algorithm.
  • To extend self-organizing map capabilities to spatiotemporal signal processing.
  • To elucidate the self-organization principles underlying cortical signal representations.

Main Methods:

  • Development of the time-organized map (TOM) algorithm, an extension of the SOM.
  • Incorporation of neural dynamics, specifically propagating waves, to integrate temporal and spatial information.

Related Experiment Videos

  • Modeling the transfer of temporal signal distances into spatial distances within topographic neural representations.

    • Main Results:

    • The TOM algorithm demonstrates how dynamic neural networks can self-organize to embed spatial signals within a temporal context, achieving functional invariances.
    • It predicts the emergence of time-organized representational structures in cortical areas processing temporally related signals.
    • The algorithm suggests that signal interaction strength dictates the type of topology (spatial or temporal) in topographic maps.

    Conclusions:

    • The TOM algorithm provides a biologically plausible framework for understanding spatiotemporal signal processing in neural networks.
    • It offers insights into the self-organization of cortical representations and the formation of topographic maps.
    • The findings support explanations for topographic reorganization based on time-to-space transformations.