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

A new evolutionary system for evolving artificial neural networks.

X Yao1, Y Liu

  • 1Sch. of Comput. Sci., New South Wales Univ., Canberra, ACT.

IEEE Transactions on Neural Networks
|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

Deep learning-based automated assessment of pulmonary artery indices and surgical approach triage for tetralogy of Fallot from multicenter cardiac computed tomography (CT).

Clinical radiology·2026
Same author

Incommensurate Magnetism Drives Singular Angular Magnetoresistance in the Magnetic Weyl Semimetal CeAlGe.

Physical review letters·2026
Same author

Effects of Tween 80 on three enzymes' activity in ibuprofen degradation: an insight into molecular docking and MD simulations.

SAR and QSAR in environmental research·2025
Same author

The Use of Molecular Tools for Identifying and Guiding Treatment of Cancers of Unknown Primary: A Systematic Review.

Clinical oncology (Royal College of Radiologists (Great Britain))·2025
Same author

ITGAM and FCGR3B contribute to recurrent and limited CRSwNP in children through phagosome pathway.

Rhinology·2025
Same author

[Clinical analysis of 4 cases of juvenile dermatomyositis complicated with massive hemorrhage of digestive tract].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2025
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

EPNet, a novel evolutionary system, evolves artificial neural networks (ANNs) by focusing on behavior. This approach yields compact ANNs with strong generalization capabilities across various machine learning tasks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Artificial neural networks (ANNs) are powerful computational models.
  • Evolving ANN architectures and weights presents significant challenges.
  • Previous methods often focused on structure rather than behavior.

Purpose of the Study:

  • To introduce EPNet, a new evolutionary system for evolving ANNs.
  • To emphasize the evolution of ANN behaviors over solely structural changes.
  • To improve the efficiency and effectiveness of ANN evolution.

Main Methods:

  • Utilizing Fogel's evolutionary programming (EP) as the core algorithm.
  • Implementing five novel mutation operators designed to evolve network behaviors.

Related Experiment Videos

  • Simultaneously evolving ANN architectures and connection weights, including biases.
  • Encouraging parsimony by prioritizing node/connection deletion over addition.

    • Main Results:

    • EPNet demonstrated success on benchmark problems including parity, medical diagnosis, credit assessment, and time series prediction.
    • The system produced highly compact ANNs.
    • Evolved ANNs exhibited superior generalization abilities compared to other algorithms.
    • Reduced noise in fitness evaluation through simultaneous evolution of architecture and weights.

    Conclusions:

    • EPNet offers an effective approach to evolving artificial neural networks with a focus on behavior.
    • The system achieves competitive performance, generating compact and generalizable ANNs.
    • EPNet provides a valuable alternative for tasks requiring efficient and adaptable neural network models.