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 adaptive learning algorithm for principal component analysis.

L H Chen1, S Chang

  • 1Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu.

IEEE Transactions on Neural Networks
|January 1, 1995
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

[Role of thyroid peroxidase autoantibody in the comorbidities of pemphigus vulgaris and Hashimoto thyroiditis].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2025
Same author

Adaptive photosynthetic strategies of the invasive plant <i>Sphagneticola trilobata</i> and its hybrid to a low-light environment.

Photosynthetica·2024
Same author

[Analysis of problems and management of <i>in vitro</i> diagnostic reagent clinical trials in medical laboratory].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2024
Same author

[A multicenter study on the effects of congenital cytomegalovirus infection on hearing loss].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2024
Same author

[A cross-sectional survey on the allocation of nursing human resources in burn centers in China].

Zhonghua shao shang yu chuang mian xiu fu za zhi·2023
Same author

[Progress in surgical treatment of hepatocellular carcinoma with tumor thrombus in the inferior vena cava].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2023
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 an adaptive learning algorithm (ALA) for principal component analysis (PCA). ALA offers faster convergence to principal component vectors compared to conventional methods like Sanger's GHA, especially when learning rates are not optimal.

Area of Science:

  • Machine Learning
  • Data Science
  • Signal Processing

Background:

  • Principal Component Analysis (PCA) is a widely used feature extraction technique.
  • Conventional PCA algorithms often suffer from slow convergence or divergence due to improper learning rate selection.
  • Existing algorithms like Sanger's generalized Hebbian algorithm (GHA) have limitations in convergence speed and stability.

Purpose of the Study:

  • To propose a novel adaptive learning algorithm (ALA) for Principal Component Analysis.
  • To address the convergence issues of conventional PCA algorithms.
  • To demonstrate the improved performance of ALA over existing methods.

Main Methods:

  • Development of an Adaptive Learning Algorithm (ALA) for PCA.
  • Adaptive selection of learning rate parameters within the ALA.

Related Experiment Videos

  • Comparative analysis with Sanger's generalized Hebbian algorithm (GHA).

    • Main Results:

    • The ALA demonstrates rapid convergence of weight vectors to the principal component vectors.
    • ALA achieves convergence at nearly the same rates for multiple principal components.
    • Simulations show ALA outperforms GHA in finding principal component vectors, where GHA fails.

    Conclusions:

    • The proposed ALA is an effective method for principal component extraction.
    • ALA provides a robust and efficient alternative to conventional PCA algorithms.
    • Adaptive learning rates significantly enhance the performance and stability of PCA.