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

An orthogonal neural network for function approximation.

S S Yang1, C S Tseng

  • 1Dept. of Mech. Eng., Nat. Central Univ., Chung-Li.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|January 1, 1996
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

[Analysis of allergen-specific IgE test results in children with allergic diseases in a women and children's hospital in Qingdao City].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2026
Same author

[The association between daily housework and all-cause mortality among rural older adults in Miyun District of Beijing].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2026
Same author

[Progress in the methodology and application of quantitative assessment of the healthy lifestyle score].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same author

[Correlation between serum uric acid-to-high-density lipoprotein cholesterol ratio and risk of all-cause death or cardiovascular disease death in urban and rural elderly of Beijing].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same author

[Association between hypertension subtypes and risk for all-cause mortality and cardio-cerebrovascular mortality in the elderly in communities of Beijing].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same author

[Association between remnant cholesterol and cardio-cerebrovascular mortality in the elderly in communities of Beijing].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same journal

Strategic Ability Updating in Concurrent Games by Coalitional Commitment.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2015
Same journal

Meta-Analysis of the First Facial Expression Recognition Challenge.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Adjustable model-based fusion method for multispectral and panchromatic images.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

A New Adaptive Fast Cellular Automaton Neighborhood Detection and Rule Identification Algorithm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
See all related articles

A novel single-layer neural network using orthogonal functions offers rapid training and accurate function approximation. This approach overcomes limitations of traditional feedforward networks, simplifying design and improving performance.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Traditional feedforward neural networks face challenges with initial weight determination and defining network architecture (layers, processing elements).
  • These complexities can hinder efficient training and application of neural network models.

Purpose of the Study:

  • To introduce a new single-layer neural network architecture based on orthogonal functions.
  • To address and overcome the inherent difficulties associated with traditional feedforward neural network design and training.

Main Methods:

  • Development of a single-layer neural network model leveraging orthogonal functions.
  • The number of processing elements is determined by the required output accuracy.
  • Unique weight properties facilitate rapid convergence during training.

Related Experiment Videos

Main Results:

  • Experimental validation through approximation of continuous and discrete functions.
  • Demonstrated excellent performance in terms of convergence speed.
  • Achieved low approximation errors, indicating high accuracy.

Conclusions:

  • The proposed orthogonal function-based neural network provides an effective alternative to traditional feedforward networks.
  • The model exhibits superior performance in convergence time and approximation accuracy.
  • Its design simplifies the determination of network parameters, making it more practical for various applications.