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

Feedforward neural network construction using cross validation.

R Setiono1

  • 1School of Computing, National University of Singapore, Singapore 117543. rudys@comp.nus.edu.sg

Neural Computation
|November 14, 2001
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

Recursive neural network rule extraction for data with mixed attributes.

IEEE transactions on neural networks·2008
Same author

A connectionist approach to generating oblique decision trees.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
Same author

Extracting M-of-N rules from trained neural networks.

IEEE transactions on neural networks·2008
Same author

Extraction of rules from artificial neural networks for nonlinear regression.

IEEE transactions on neural networks·2008
Same author

A comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders.

Artificial intelligence in medicine·2000
Same author

Generating concise and accurate classification rules for breast cancer diagnosis.

Artificial intelligence in medicine·2000
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces a novel algorithm for building feedforward neural networks for pattern classification. The method adaptively adds hidden units, improving predictive accuracy over decision tree approaches.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computer Science

Background:

  • Pattern classification is a fundamental problem in machine learning.
  • Traditional methods like decision trees have limitations in accuracy.
  • Feedforward neural networks offer a powerful alternative for complex classification tasks.

Purpose of the Study:

  • To present a new algorithm for constructing single-hidden-layer feedforward neural networks.
  • To enhance predictive accuracy in pattern classification using an adaptive network construction approach.
  • To compare the algorithm's performance against state-of-the-art decision tree methods.

Main Methods:

  • The algorithm incrementally adds hidden units to a feedforward neural network.
  • Cross-validation using a subset of training samples determines when to stop adding units.

Related Experiment Videos

  • New units are added only if they improve accuracy on both training and validation sets.

    • Main Results:

    • The proposed algorithm effectively constructs feedforward neural networks.
    • Experimental results demonstrate superior predictive accuracy compared to decision tree methods.
    • The adaptive nature of the algorithm leads to optimized network performance.

    Conclusions:

    • The presented algorithm offers an effective strategy for pattern classification.
    • It achieves higher predictive accuracy than existing decision tree techniques.
    • This approach provides a robust method for building efficient neural networks.