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

Clustering irregular shapes using high-order neurons.

H Lipson1, H T Siegelmann

  • 1Mechanical Engineering Department, Technion-Israel Institute of Technology, Haifa, Israel.

Neural Computation
|October 14, 2000
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

Diagnostic accuracy of the Cepheid MTB host response assay for the detection of pulmonary TB.

IJTLD open·2025
Same author

The global landscape of cognition: hierarchical aggregation as an organizational principle of human cortical networks and functions.

Scientific reports·2015
Same author

Rapid 3D printing of anatomically accurate and mechanically heterogeneous aortic valve hydrogel scaffolds.

Biofabrication·2012
Same author

X-ray diffraction in inorganic chemistry, metallurgy and mineralogy.

Nature·2010
Same author

A computational environment to simulate complex tendinous topologies.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2007
Same author

Three generations of automatically designed robots.

Artificial life·2001
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study presents a novel high-order neuron method for clustering complex data shapes. This approach effectively distinguishes even overlapping data clusters, outperforming classic methods on the Iris dataset.

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Data analysis

Background:

  • Traditional clustering methods struggle with irregularly shaped and overlapping data.
  • Classic neurons have limitations in modeling complex data geometries.

Purpose of the Study:

  • To introduce a new method for clustering irregularly shaped data using high-order neurons.
  • To demonstrate the capability of high-order neurons in modeling complex analytical shapes.
  • To enable effective decomposition of challenging data cluster arrangements.

Main Methods:

  • Replacing classic synaptic weights with high-order tensors in homogeneous coordinates.
  • Formulating high-order shapes based on the maximum-correlation activation principle.
  • Implementing simple local Hebbian learning for neuron training.

Related Experiment Videos

  • Applying the method to decompose spatial data cluster arrangements.

    • Main Results:

    • The high-order neuron model successfully represents complex shapes, including first-order (classic) and second-order (ellipsoidalmetric) neurons.
    • The method allows for simple local Hebbian learning.
    • Demonstrated effective decomposition of spatial data clusters, including very close and partially overlapping ones.
    • Achieved superior clustering results on the Iris dataset compared to classic neurons.

    Conclusions:

    • High-order neurons offer a powerful framework for advanced data clustering.
    • This method enhances the ability to analyze and separate complex and overlapping data patterns.
    • The approach shows significant potential for applications in pattern recognition and data analysis.