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

Divide-and-conquer learning and modular perceptron networks.

H C Fu¹, Y P Lee, C C Chiang

¹Department of Computer Science and Information Engineering, National Chiao Tung University, Hsinchu, Taiwan 300, R.O.C.

IEEE Transactions on Neural Networks

|February 5, 2008

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

Probable obsessive-compulsive disorder among youth in Singapore: Prevalence, sociodemographic correlates, and the association with psychological distress, harmful alcohol use and functional impairment.

Comprehensive psychiatry·2026

Same author

Examining psychological distress among youth in Singapore: Insights from the National Youth Mental Health Study.

Asian journal of psychiatry·2025

Same author

Unequivocal Identification of Spin-Triplet and Spin-Singlet Superconductors with Upper Critical Field and Flux Quantization.

Physical review letters·2023

Same author

[Predicting response to non-small cell lung cancer immunotherapy using pre-treatment contrast-enhanced CT texture-based classification].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2021

Same author

Absence of Evidence of Electrical Switching of the Antiferromagnetic Néel Vector.

Physical review letters·2019

Same author

Long-term follow-up of intradermal injection of methylene blue for intractable, idiopathic pruritus ani.

Techniques in coloproctology·2019

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 modular perceptron network (MPN) with divide-and-conquer learning (DCL) overcomes local minima in neural network training. This approach improves learning performance, generalization, and reduces processing time for complex datasets.

Area of Science:

Artificial Intelligence
Machine Learning
Neural Networks

Background:

Multilayer perceptron training can stall in local minima or flat regions.
Existing neural network designs may struggle with complex, non-linear data patterns.

Purpose of the Study:

To introduce a novel modular perceptron network (MPN) and divide-and-conquer learning (DCL) schemes.
To enhance the training efficiency and generalization capabilities of modular neural networks.

Main Methods:

The DCL scheme recursively partitions data regions when training stalls.
A self-growing perceptron network is constructed for new data regions, while the original network retrains on remaining data.
Iterative partitioning, weight estimation, and learning are employed until complete data learning.

Related Experiment Videos

Main Results:

The MPN demonstrated superior weight learning performance, requiring fewer data presentations during training.
The proposed MPN achieved better generalization performance compared to representative neural networks.
Reduced processing time was observed during the retrieving phase with the MPN.

Conclusions:

The MPN with DCL offers an effective solution for overcoming training limitations in neural networks.
This modular approach enhances both learning efficiency and predictive accuracy.
The MPN presents a promising advancement for designing robust and efficient neural network architectures.