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

Template learning of cellular neural network using genetic programming.

Elsayed Radwan1, Eiichiro Tazaki

  • 1Department of Control and System Engineering, Toin University of Yokohama, 1614 Kurogane-cho, Aoba-ku, Yokohama 225-8502, Japan. radwan@intlab.toin.ac.jp

International Journal of Neural Systems
|September 17, 2004
PubMed
Summary

A novel learning algorithm for space invariant Uncoupled Cellular Neural Networks uses Genetic Programming to optimize control actions. This approach enables the exploration of stable domains by deriving effective Cloning Templates.

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

Rough sets and genetic algorithms in learning cellular neural networks cloning template for decision making system.

International journal of neural systems·2004
Same author

Decision making using hybrid rough sets and neural networks.

International journal of neural systems·2003
See all related articles

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Cellular Neural Networks (CNNs) are powerful tools for image processing and complex system modeling.
  • Uncoupled CNNs offer unique computational properties but require efficient learning methods.
  • Developing adaptive learning algorithms is crucial for expanding CNN applications.

Purpose of the Study:

  • Introduce a new learning algorithm for space-invariant Uncoupled Cellular Neural Networks (CNNs).
  • Formulate the learning process as an optimization problem to discover optimal network behavior.
  • Utilize Genetic Programming to generate novel and effective control rules for CNNs.

Main Methods:

  • Employed Genetic Programming (GP) to derive the Cloning Template for lattice CNN architectures.

Related Experiment Videos

  • Formulated network learning as an optimization problem, leveraging GP's ability to explore diverse solution spaces.
  • The algorithm allows for exploration of any stable domain within the CNN's operational parameters.

    • Main Results:

    • Demonstrated the successful application of the proposed learning algorithm in deriving Cloning Templates.
    • Showcased the algorithm's capability to discover new control rules, both incremental and novel.
    • Presented several application results validating the effectiveness of the developed approach.

    Conclusions:

    • The introduced learning algorithm provides an effective method for training space-invariant Uncoupled Cellular Neural Networks.
    • Genetic Programming is a suitable technique for knowledge discovery and rule generation in CNNs.
    • The approach facilitates the exploration of stable operational domains, enhancing CNN adaptability and performance.