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

Neural network application for direct feedback controllers.

Y Ichikawa1, T Sawa

  • 1Energy Res. Lab., Hitachi Ltd., Ibaraki.

IEEE Transactions on Neural Networks
|January 1, 1992
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

Correction to: Radiofrequency identification tag system improves the efficiency of closed vitrification for cryopreservation and thawing of bovine ovarian tissues.

Journal of assisted reproduction and genetics·2020
Same author

Anaesthesia-dependent oscillatory EEG features in the super-elderly.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2020
Same author

Radiofrequency identification tag system improves the efficiency of closed vitrification for cryopreservation and thawing of bovine ovarian tissues.

Journal of assisted reproduction and genetics·2019
Same author

Hyperglycaemia augments lipopolysaccharide-induced reduction in rat and human macrophage phagocytosis via the endoplasmic stress-C/EBP homologous protein pathway.

British journal of anaesthesia·2019
Same author

mTOR signaling controls VGLUT2 expression to maintain pain hypersensitivity after tissue injury.

Neuroscience·2015
Same author

Comparative study of Poincaré plot analysis using short electroencephalogram signals during anaesthesia with spectral edge frequency 95 and bispectral index.

Anaesthesia·2014
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 introduces a novel learning algorithm for perceptron-like neural networks using modified genetic algorithms. This approach enables networks to optimize plant responses through simulated evolution, discovering advanced control strategies.

Area of Science:

  • Artificial Intelligence
  • Control Systems Engineering
  • Computational Neuroscience

Background:

  • Perceptron-like neural networks offer potential for direct plant control, similar to feedback controllers.
  • A key challenge is optimizing network learning for global plant response evaluation.
  • Existing methods lack efficient mechanisms for complex, arbitrary optimization goals.

Purpose of the Study:

  • To develop a learning algorithm for perceptron-like neural networks directly connected to plants.
  • To enable networks to optimize global plant responses using a simulated evolution process.
  • To explore the capabilities of genetic algorithms in enhancing neural network learning for control.

Main Methods:

  • Modification of genetic algorithms to facilitate neural network learning.

Related Experiment Videos

  • Implementation of a simulated evolution process involving crossover and mutation of connection weights.
  • Assignment of fitness values based on global evaluation of plant responses.

    • Main Results:

    • Demonstrated optimization of neural networks for diverse evaluation criteria.
    • Successful discovery of self-organized control schemes, including state estimation.
    • Validation of the algorithm's effectiveness in discovering nonlinear control strategies.

    Conclusions:

    • Modified genetic algorithms provide an effective method for training perceptron-like neural networks in plant control.
    • The simulated evolution approach allows networks to autonomously develop sophisticated control and estimation capabilities.
    • This learning paradigm holds promise for advancing intelligent control systems in complex environments.