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

Hierarchical classification with a competitive evolutionary neural tree.

R G. Adams1, K Butchart, N Davey

  • 1School of Information Sciences, University of Hertfordshire, Hatfield, UK

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
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

The application of machine learning to the modelling of percutaneous absorption: an overview and guide.

SAR and QSAR in environmental research·2015
Same author

The application of discriminant analysis and Machine Learning methods as tools to identify and classify compounds with potential as transdermal enhancers.

European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences·2011
Same author

What do we know about how humans cough?

Pulmonary pharmacology & therapeutics·2004
Same author

T-cell recognition of mycobacterial GroES peptides in Thai leprosy patients and contacts.

Infection and immunity·1998
Same author

Measurement of cytotoxic T lymphocyte precursor frequencies reveals cryptic HLA class I mismatches in the context of unrelated donor bone marrow transplantation.

Transplantation·1997
Same author

Paediatric bereavement care.

Paediatric nursing·1995
Same journal

A boundary-regularization-enhanced video anomaly detection network based on context-adaptive spatio-temporal conditional diffusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

MT<sup>2</sup>-CSD and LLM-CRAN: A new dataset and an LLM-based multi-semantic knowledge fusion model for conversational stance detection.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TriAlignNet: A triple-path cross-modality alignment framework for multimodal time series forecasting.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

A novel Competitive Evolutionary Neural Tree (CENT) network offers dynamic, hierarchical classification for unlabeled data. This self-structuring network eliminates the need for external parameters, creating stable classifications using local heuristics.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Hierarchical classification of unlabeled data is challenging.
  • Existing competitive networks often require predefined structures or parameters.

Purpose of the Study:

  • Introduce a novel dynamic, tree-structured network called the Competitive Evolutionary Neural Tree (CENT).
  • Enable self-determination of network structure and node count without external parameters.
  • Achieve stable hierarchical classification for unlabeled datasets.

Main Methods:

  • Developed a dynamic, tree-structured neural network architecture (CENT).
  • Implemented self-structuring capabilities for competitive nodes.
  • Utilized locally calculated heuristics to control network growth and ensure stability.

Related Experiment Videos

Main Results:

  • The CENT network successfully provided hierarchical classification for unlabeled datasets.
  • Demonstrated the ability to self-determine the number and structure of competitive nodes.
  • Achieved stable classificatory structures through heuristic-based growth halting.
  • Validated performance across various datasets, including Anderson's IRIS dataset.

Conclusions:

  • The CENT network is a capable tool for hierarchical classification of unlabeled data.
  • Its self-structuring and parameter-free nature offer significant advantages over existing methods.
  • The network reliably produces representative hierarchical structures for diverse datasets.