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

Quick fuzzy backpropagation algorithm.

A Nikov1, S Stoeva

  • 1Technical University of Sofia, Bulgaria. nikov@tu-sofia.acad.bg

Neural Networks : the Official Journal of the International Neural Network Society
|April 24, 2001
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

Applicability of augmented reality in perioperative liver resection.

Rozhledy v chirurgii : mesicnik Ceskoslovenske chirurgicke spolecnosti·2026
Same author

Surgery of extrahepatic bile duct cancer - current evidence and recommendations.

Rozhledy v chirurgii : mesicnik Ceskoslovenske chirurgicke spolecnosti·2022
Same author

Minimally invasive pancreatic resection in the light of evidence state of the art.

Rozhledy v chirurgii : mesicnik Ceskoslovenske chirurgicke spolecnosti·2021
Same author

Pancreatic head resections in the setting of celiac axis stenosis: Case report and review of literature.

Rozhledy v chirurgii : mesicnik Ceskoslovenske chirurgicke spolecnosti·2021
Same author

[Treatment of acute appendicitis: Retrospective analysis].

Rozhledy v chirurgii : mesicnik Ceskoslovenske chirurgicke spolecnosti·2016
Same author

[Rare situations in treatment of polytraumatised patients - case reports].

Rozhledy v chirurgii : mesicnik Ceskoslovenske chirurgicke spolecnosti·2016

A new QuickFBP algorithm offers faster neural network training than fuzzy backpropagation (FBP). This enhanced fuzzy backpropagation method achieves polynomial time complexity, enabling quicker adaptation for interactive systems and data mining applications.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Intelligence

Background:

  • Fuzzy backpropagation (FBP) algorithms are utilized in neural networks.
  • Existing FBP algorithms can exhibit exponential time complexity, limiting training speed.

Purpose of the Study:

  • To introduce the QuickFBP algorithm, a modification of FBP with improved computational efficiency.
  • To analyze and prove the convergence conditions for QuickFBP and FBP algorithms.
  • To demonstrate the practical applicability of QuickFBP in adaptive interactive systems.

Main Methods:

  • Development of the QuickFBP algorithm, optimizing net function computation.
  • Theoretical analysis and proof of convergence for both QuickFBP and FBP algorithms.
  • Simulation experiments on neural networks, including large-scale examples.

Related Experiment Videos

Main Results:

  • QuickFBP demonstrates polynomial time complexity, significantly outperforming FBP's exponential complexity.
  • Convergence is proven for QuickFBP and FBP under specific conditions for single and multiple output networks.
  • Simulations confirm faster training speeds for QuickFBP, especially in large neural networks.

Conclusions:

  • QuickFBP offers a substantial speed improvement over FBP for neural network training.
  • The algorithm's quasi-unsupervised learning capability broadens its applicability.
  • QuickFBP is suitable for adaptive interactive systems, data mining, and other intelligent applications.