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

STRIP--a strip-based neural-network growth algorithm for learning multiple-valued functions.

A Ngom1, I Stojmenović, V Milutinović

  • 1Computer Science Department, University of Windsor, Windsor, ONN9B 3P4, Canada. angom@cs.uwindsor.ca

IEEE Transactions on Neural Networks
|February 5, 2008
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

[Smoking among women in Africa].

Revue d'epidemiologie et de sante publique·2013
Same author

[Clinical manifestations related to kitchen biomass smoke in African women].

Revue des maladies respiratoires·2012
Same author

[Tuberculous orchi-epididymitis. Report of 2 cases registered in pneumology at the Chu de Cocody].

Le Mali medical·2010
Same author

On the number of multilinear partitions and the computing capacity of multiple-valued multiple-threshold perceptrons.

IEEE transactions on neural networks·2008
Same author

[Smoking in school: Cocody, Abidjan].

Revue de pneumologie clinique·2007
Same author

[Epidemiological, clinical and biological profile of resistant or recurrent pulmonary tuberculosis in Abidjan].

Bulletin de la Societe de pathologie exotique (1990)·2005
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 genetic algorithm (GA) for synthesizing multiple-valued logic functions using neural networks. The GA partitions input space into strips, enabling accurate function computation by hidden units.

Area of Science:

  • * Computational intelligence and machine learning.
  • * Artificial neural networks and logic synthesis.

Background:

  • * Synthesizing multiple-valued logic functions is crucial for advanced computing.
  • * Existing methods may lack efficiency or scalability for complex functions.

Purpose of the Study:

  • * To develop a novel method for synthesizing multiple-valued logic functions using neural networks.
  • * To leverage genetic algorithms for efficient neural network construction.

Main Methods:

  • * A genetic algorithm (GA) is employed to identify the longest strips in a defined space V.
  • * These strips, bounded by hyperplanes, correspond to hidden units in the neural network.
  • * The space V is partitioned into strips via repeated GA application.

Related Experiment Videos

Main Results:

  • * Two neural networks were constructed utilizing the identified hidden units.
  • * These networks demonstrated the ability to correctly compute arbitrary multiple-valued logic functions.
  • * Preliminary experimental results validate the proposed approach.

Conclusions:

  • * The proposed GA-based method offers a viable approach for synthesizing multiple-valued logic functions.
  • * The constructed neural networks effectively represent and compute these complex functions.
  • * Further research and experimentation are warranted to explore broader applications.