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

A neural network model which combines unsupervised and supervised learning.

K R Hsieh¹, W T Chen

¹Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu.

IEEE Transactions on Neural Networks

|January 1, 1993

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

[Effectiveness and safety of belumosudil in 20 patients with chronic graft-versus-host disease].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2025

Same author

Transport processes and coalescence of two entrapping bubbles during upward solidification.

Heliyon·2025

Same author

[Exploring the causality between intestinal flora and hyperplastic scars of human based on two-sample Mendelian randomization analysis].

Zhonghua shao shang yu chuang mian xiu fu za zhi·2024

Same author

Effects of treatment processes on AOC removal and changes of bacterial diversity in a water treatment plant.

Journal of environmental management·2022

Same author

Author Correction: Slow light nanocoatings for ultrashort pulse compression.

Nature communications·2021

Same author

Slow light nanocoatings for ultrashort pulse compression.

Nature communications·2021

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

A novel hierarchical self-organization map combines unsupervised and supervised learning for enhanced pattern recognition. This hybrid approach improves discrimination of similar patterns and generalizes well.

Area of Science:

Artificial Intelligence
Machine Learning
Neural Networks

Background:

Pattern recognition is crucial in many AI applications.
Existing methods may struggle with discriminating similar patterns.
Hierarchical self-organization maps offer a framework for unsupervised learning.

Purpose of the Study:

To propose a novel neural network architecture for pattern recognition.
To enhance the discrimination of similar patterns using a hybrid learning approach.
To evaluate the generalization capability of the proposed model.

Main Methods:

A hierarchical self-organization map was developed.
The network was initially trained using unsupervised learning.
Supervised learning was applied to adjust scaling factors for feature discrimination when needed.

Related Experiment Videos

Main Results:

The proposed neural network demonstrated good generalization capability.
The model achieved sharp discrimination between similar patterns.
Simulation results validated the effectiveness of the hybrid learning approach.

Conclusions:

The combination of unsupervised and supervised learning in a hierarchical self-organization map is effective for pattern recognition.
The proposed model successfully addresses the challenge of discriminating similar patterns.
This approach offers a promising direction for developing robust pattern recognition systems.