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

Removing irrelevant features in neural network classification using evolutionary computations.

I Ciuca1, J A Ware, A Cristea

  • 1Research Institute for Informatics, Bucharest, Romania.

Studies in Health Technology and Informatics
|December 8, 1996
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

Polyhydroxybutyrate production by an extremely halotolerant Halomonas elongata strain isolated from the hypersaline meromictic Fără Fund Lake (Transylvanian Basin, Romania).

Journal of applied microbiology·2018
Same author

Commentary on: "Influence of OATP1B1 Function on the Disposition of Sorafenib-β-D-Glucuronide".

Clinical and translational science·2017
Same author

Validation and determination of taselisib, a β-sparing phosphoinositide 3-kinase (PI3K) inhibitor, in human plasma by LC-MS/MS.

Journal of pharmaceutical and biomedical analysis·2016
Same author

A supported liquid extraction-LC-MS/MS method for determination of GDC-0980 (Apitolisib), a dual small-molecule inhibitor of class 1A phosphoinositide 3-kinase and mammalian target of rapamycin, in human plasma.

Journal of pharmaceutical and biomedical analysis·2014
Same author

Response to "Drug interactions produced by proton pump inhibitors: not simply a pH effect".

Clinical pharmacology and therapeutics·2012
Same author

Drug absorption interactions between oral targeted anticancer agents and PPIs: is pH-dependent solubility the Achilles heel of targeted therapy?

Clinical pharmacology and therapeutics·2012
Same journal

A GenAI Pipeline for Violinist Kinematic Data Management.

Studies in health technology and informatics·2026
Same journal

AMAL-For-Qatar: A Comprehensive AI Ecosystem for Fetal Ultrasound Analysis - Project Overview and Achievements.

Studies in health technology and informatics·2026
Same journal

Longitudinal Treatment-Aware Multimodal AI for Dermatology: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Predicting Postpartum Depression Using Imbalance-Aware Machine Learning.

Studies in health technology and informatics·2026
Same journal

Validation of Deep-Learning Models for Autosegmentation of Brain Metastases.

Studies in health technology and informatics·2026
Same journal

Delay-Dependent Gating in Modular RNNs.

Studies in health technology and informatics·2026
See all related articles

Evolutionary artificial neural networks (EANN) combine learning with evolution for adaptation. This study applies evolutionary programming to optimize multilayer perceptrons (MLP) by evolving both input structure and weights.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Artificial neural networks (ANN) are computational models inspired by biological neural networks.
  • Learning is a primary adaptation mechanism in ANNs.
  • Evolutionary computations offer powerful population-based search capabilities for complex optimization tasks.

Purpose of the Study:

  • To introduce a novel application of evolutionary programming for ANN.
  • To simultaneously evolve the input structure and weights of multilayer feed-forward perceptrons (MLP).
  • To enhance the adaptive capabilities of ANNs by integrating evolutionary principles.

Main Methods:

  • Application of evolutionary programming techniques.
  • Simultaneous optimization of MLP input structure and weights.

Related Experiment Videos

  • Utilizing standard sigmoidal activation functions within the MLP architecture.

    • Main Results:

    • Demonstrated the feasibility of using evolutionary programming for MLP structure and weight evolution.
    • Showcased the potential for EANNs to outperform traditional ANNs in specific tasks.
    • Provided a method for automated network design and parameter tuning.

    Conclusions:

    • Evolutionary artificial neural networks (EANN) represent a significant advancement in ANN adaptation.
    • The proposed method effectively optimizes MLP by evolving both structure and weights.
    • This approach offers a promising direction for developing more sophisticated and adaptive AI systems.