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

An optimization methodology for neural network weights and architectures.

Teresa B Ludermir1, Akio Yamazaki, Cleber Zanchettin

  • 1Center of Informatics, Federal University of Pernambuco, Pernambuco 50740-540, Brazil. tbl@cin.ufpe.br

IEEE Transactions on Neural Networks
|November 30, 2006
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

Biventricular and biatrial assessment using low-dose cine computed tomography during recirculation phase of contrast agent: Comparison to cine cardiac magnetic resonance.

Journal of cardiovascular computed tomography·2026
Same author

A digital archive reveals how a funding agency cooperated with academics to support the nascent field of genomics.

Nature communications·2026
Same author

Fall Detection Based on Computer Vision: A Systematic Mapping Study.

IEEE journal of biomedical and health informatics·2026
Same author

Diagnostic Improvement in Endoleak Detection: The Role of Low-energy Virtual Monochromatic CT and Deep Learning Reconstruction.

Journal of imaging informatics in medicine·2026
Same author

Respiratory Muscle Strength and Imaging Parameters in Smokers: A Prospective Observational Study.

International journal of chronic obstructive pulmonary disease·2026
Same author

Quantifying cross-site effect in AI-based dental age estimation: evidence from Brazilian panoramic radiographs.

Dento maxillo facial radiology·2026
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

This study presents a novel neural network optimization method. It simultaneously optimizes weights and architectures for efficient, high-performance classification across diverse datasets.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Neural network design involves complex weight and architecture optimization.
  • Existing methods often struggle with balancing network complexity and classification accuracy.
  • Automated processes are needed for efficient neural network development.

Purpose of the Study:

  • To introduce a global optimization methodology for neural networks.
  • To simultaneously optimize multilayer perceptron (MLP) network weights and architectures.
  • To generate network topologies with minimal connections and high classification performance.

Main Methods:

  • Combines simulated annealing, tabu search, and backpropagation.
  • Develops an automated process for network generation.

Related Experiment Videos

  • Focuses on optimizing both network structure and parameters.

    • Main Results:

    • Achieved superior results on four classification and one prediction problem.
    • Demonstrated improved performance compared to common optimization techniques.
    • Generated networks with high classification accuracy and low complexity.

    Conclusions:

    • The proposed methodology offers an effective approach to neural network global optimization.
    • Simultaneous optimization of weights and architecture leads to efficient and accurate models.
    • This technique provides a robust solution for developing high-performing, low-complexity neural networks.