Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Ensemble competitive learning neural networks with reduced input dimension

J Kim¹, J Ahn, S Cho

¹Department of Computer Science, Taegu University, Kyungpook, Korea.

International Journal of Neural Systems

|June 1, 1995

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 importance of HPV testing in oropharyngeal cancer in two US populations.

Neoplasia (New York, N.Y.)·2026

Same author

Improving accuracy of pterygoid plate resection using real-time navigated piezoelectric surgery and a three-dimensionally printed guide.

International journal of oral and maxillofacial surgery·2026

Same author

A 12-year review of equestrian related injuries at a major trauma centre in South Africa.

South African journal of surgery. Suid-Afrikaanse tydskrif vir chirurgie·2026

Same author

Foley catheter balloon tamponade for actively bleeding wounds following penetrating neck injury: a systematic review and meta-analysis.

Annals of the Royal College of Surgeons of England·2025

Same author

Principles for management of hip fracture for older adults taking direct oral anticoagulants: an international consensus statement.

Anaesthesia·2024

Same author

Disease burden of bacteraemia with extended-spectrum beta-lactamase-producing and carbapenem-resistant Enterobacterales in Korea.

The Journal of hospital infection·2023

Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026

Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026

Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026

Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026

Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026

Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026

See all related articles

This study introduces a novel ensemble competitive learning method that reduces input dimensions for improved neural network classification. Experiments show enhanced performance in remote sensing and speech data analysis.

Area of Science:

Machine Learning
Artificial Intelligence
Pattern Recognition

Background:

Conventional neural networks use all input dimensions, potentially leading to misclassification.
The contribution of each input dimension to classification is often unknown and variable.

Purpose of the Study:

To propose a new ensemble competitive learning method utilizing reduced input dimensions.
To enhance classification accuracy by leveraging information from individual input dimensions.

Main Methods:

A novel ensemble competitive learning approach is presented.
Multiple neural networks are trained on datasets with one dimension reduced.
Classification outputs from individual networks are combined using consensus schemes.
Ambiguous output neurons are eliminated to improve accuracy.

Related Experiment Videos

Main Results:

The proposed method demonstrates improved classification performance.
Experimental validation was conducted using remote sensing and speech datasets.
The ensemble approach effectively combines information from reduced dimensions.

Conclusions:

Reduced input dimension ensemble learning offers superior classification accuracy.
The method effectively handles varying attribute contributions in input data.
This approach shows promise for complex pattern recognition tasks.