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

Selecting optimal experiments for multiple output multilayer perceptrons

L M Belue1, K W Bauer, D W Ruck

  • 1Department of Operational Sciences, Department of the Air Force, Air Force Institute of Technology, Wright Patterson AFB, OH 45433-7765, USA.

Neural Computation
|January 1, 1997
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

Experience and expectations of patients on weight loss: The Learning Health System Network Experience.

Obesity science & practice·2019
Same author

Remission of obesity among a nationally representative sample of US children.

Pediatric obesity·2018
Same author

Interrelationships of child appetite, weight and snacking among Hispanic preschoolers.

Pediatric obesity·2016
Same author

Cardio-metabolic risk screening among adolescents: understanding the utility of body mass index, waist circumference and waist to height ratio.

Pediatric obesity·2014
Same author

Relationships between the family environment and school-based obesity prevention efforts: can school programs help adolescents who are most in need?

Health education research·2011
Same author

Use of artificial neural networks for Hartmann-sensor lenslet centroid estimation.

Applied optics·2010
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

Researchers can optimize experimental design for multilayer perceptrons (MLPs) by selecting specific data points. This statistical method improves training data collection for improved MLP performance in classification tasks.

Area of Science:

  • Machine Learning
  • Statistics
  • Experimental Design

Background:

  • Multilayer perceptrons (MLPs) are widely used for classification.
  • Effective training data is crucial for MLP performance.
  • Current methods for selecting experimental design points may not be optimal.

Purpose of the Study:

  • To develop a statistical method for selecting optimal experimental design points for multiple output MLPs.
  • To improve the efficiency of training data collection for MLPs.

Main Methods:

  • Viewing MLPs as multivariate nonlinear regression models.
  • Employing a Bayesian formulation for unknown variance-covariance matrices.
  • Developing a selection criterion based on the volume of the joint confidence ellipsoid for MLP weights.

Related Experiment Videos

  • Utilizing Hadamard matrices for simplification and uncorrelated outputs.

    • Main Results:

    • The proposed statistical method identifies optimal experimental design points.
    • Optimally selected points demonstrate superiority over random or grid-based selection.
    • Hadamard matrices offer a simplified criterion for practical application.

    Conclusions:

    • Optimal experimental design significantly enhances MLP training data quality.
    • The developed criterion provides a statistically sound approach for selecting data points.
    • This method contributes to more efficient and effective development of MLPs for classification.