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

Competitive neural trees for pattern classification.

S Behnke1, N B Karayiannis

  • 1Institute of Computer Science, Free University of Berlin, 14195 Berlin, Germany.

IEEE Transactions on Neural Networks
|February 8, 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

[Spontaneous craniocervical dissection].

Der Radiologe·2021
Same author

[Time is brain : Time management in acute stroke treatment].

Der Radiologe·2019
Same author

Substantia nigra hyperechogenicity is related to decline in verbal memory in healthy elderly adults.

European journal of neurology·2016
Same author

Peri-interventional Subarachnoid Hemorrhage During Mechanical Thrombectomy with stent retrievers in Acute Stroke: A Retrospective Case-Control Study.

Clinical neuroradiology·2014
Same author

The effect of chemical stress on the polypeptide composition of the intercellular fluid of barley leaves.

Planta·2013
Same author

Cultivar-related differences in the distribution of cell-wall-bound thionins in compatible and incompatible interactions between barley and powdery mildew.

Planta·2013
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 competitive neural trees (CNeT) for pattern classification. CNeTs use unsupervised learning and hierarchical clustering for efficient, accurate data categorization.

Area of Science:

  • Computer Science
  • Machine Learning
  • Artificial Intelligence

Background:

  • Pattern classification is a fundamental task in machine learning.
  • Existing methods may face challenges with large datasets or complex patterns.
  • Hierarchical approaches offer potential for efficient data organization.

Purpose of the Study:

  • To introduce and evaluate competitive neural trees (CNeT) as a novel approach for pattern classification.
  • To demonstrate the CNeT's ability to perform hierarchical clustering and utilize unsupervised competitive learning.
  • To present efficient search methods for CNeT training and recall.

Main Methods:

  • Development of competitive neural trees (CNeT) with m-ary nodes.
  • Utilizing unsupervised competitive learning at the node level.

Related Experiment Videos

  • Employing hierarchical clustering of feature vectors and forward pruning for controlled growth.
  • Introducing novel search algorithms for efficient training and recall.

    • Main Results:

    • CNeTs demonstrate effective hierarchical clustering of feature vectors.
    • The tree structure allows for efficient prototype determination by searching only a fraction of the tree.
    • Performance evaluation shows competitive results compared to existing classifiers on various pattern classification tasks.

    Conclusions:

    • Competitive neural trees (CNeT) offer a promising new method for pattern classification.
    • The architecture facilitates efficient learning and data representation through hierarchical clustering.
    • CNeTs present a viable alternative to existing classification techniques, particularly for complex datasets.