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 genetic algorithm based on prepotency evolution using chaotic initiation used for network training.

Qing-zhang Lü1, Jian-hui Jiang, Ru-qin Yu

  • 1State Key Laboratory of Chemo/Biosensing and Chemometrics, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, P. R. China.

Journal of Chemical Information and Computer Sciences
|July 23, 2003
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

Synthetic Chimeric Antigen Lysosome-Associated Receptor Redirects Targeted Protein to Degradation.

Journal of the American Chemical Society·2026
Same author

Generalized Biosensing and Signaling Reprogramming Using Circular RNA-Protein Circuit-Mediated Cargo Release.

Analytical chemistry·2026
Same author

Recent Advances in Bacterial Separation and Enrichment from Blood for the Diagnosis of Bloodstream Infections.

Sensors (Basel, Switzerland)·2026
Same author

Synergistic Remodeling of Tumor Immune Microenvironment via a DNA Nanodevice Integrating STING Activation and Lysosome-Targeted PD-L1 Degradation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Light-Inducible Bispecific DNAzymes Reveal Mitochondrial Fe<sup>2+</sup>/Fe<sup>3+</sup> Dynamics During Ferroptosis.

Angewandte Chemie (International ed. in English)·2026
Same author

Ketal-Bridged Rhodamines as a New Scaffold for Near-Infrared Chemigenetic Indicators with Enhanced Fluorogenicity.

Journal of the American Chemical Society·2026
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
See all related articles

A novel prepotency evolution (PE) algorithm, combined with chaotic logistic mapping, enhances artificial neural network (ANN) training. This PECNN method accelerates convergence and improves global minimum discovery for molecular vibration predictions.

Area of Science:

  • Computational Chemistry
  • Artificial Intelligence
  • Evolutionary Algorithms

Background:

  • Traditional genetic algorithms (GA) can be slow and prone to overfitting.
  • Efficient training of artificial neural networks (ANNs) is crucial for complex data analysis.
  • Chaos theory offers tools for generating diverse initial conditions.

Purpose of the Study:

  • To introduce a new evolutionary algorithm called prepotency evolution (PE).
  • To combine PE with chaotic logistic mapping for training feed-forward ANNs (PECNN).
  • To evaluate PECNN's performance against conventional methods in predicting molecular vibration frequencies.

Main Methods:

  • Developed a novel prepotency evolution (PE) algorithm.
  • Integrated logistic mapping for chaotic initialization of the PE algorithm.

Related Experiment Videos

  • Applied the PE algorithm with chaotic initialization to train multi-layer feed-forward ANNs (PECNN).
  • Implicitly incorporated crossover and mutation within the PE operator.

    • Main Results:

    • The PE algorithm demonstrated faster convergence compared to conventional GA.
    • PECNN effectively identified global minima without overfitting to training data.
    • PECNN rapidly and effectively explored numerous minima, increasing the chance of finding the global minimum.
    • PECNN predictions for tetrahedral vibration modes (nu(1) and nu(2)) of tetrahalide ions showed favorable comparison with PLS regression.

    Conclusions:

    • The proposed PECNN algorithm offers a significant improvement in ANN training speed and global minimum search capability.
    • PECNN provides a robust and efficient method for analyzing complex datasets, as evidenced by molecular vibration predictions.
    • The combination of chaotic dynamics and evolutionary strategies presents a promising direction for advanced computational modeling.