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

A unified neural bigradient algorithm for robust PCA and MCA

L Wang1, J Karhunen

  • 1Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland. Liuyue.Wang@hut.fi, Juha.Karhunen@hut.fi

International Journal of Neural Systems
|March 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

Physically principled reflection models applied to filtered camera imaging inversions in metal walled fusion machines.

The Review of scientific instruments·2019
Same author

Impact of early angiographic evaluation on the frequency of emergency reoperations after coronary bypass surgery.

Scandinavian journal of surgery : SJS : official organ for the Finnish Surgical Society and the Scandinavian Surgical Society·2010
Same author

Local linear independent component analysis based on clustering.

International journal of neural systems·2001
Same author

An experimental comparison of neural algorithms for independent component analysis and blind separation.

International journal of neural systems·1999
Same author

Irregular expression of hyaluronan and its CD44 receptor is associated with metastatic phenotype in laryngeal squamous cell carcinoma.

Virchows Archiv : an international journal of pathology·1999
Same author

Least-squares methods for blind source separation based on nonlinear PCA.

International journal of neural systems·1999

A novel bigradient search algorithm efficiently computes principal and minor components using unified Hebbian learning. This method aids in robust eigenvector extraction and blind source signal separation.

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Signal processing

Background:

  • Principal Component Analysis (PCA) and Minor Component Analysis (MCA) are fundamental for dimensionality reduction and feature extraction.
  • Existing algorithms often require separate formulations for Hebbian and anti-Hebbian learning.
  • Simultaneous extraction of multiple robust eigenvectors is computationally challenging.

Purpose of the Study:

  • To introduce a new instantaneous-gradient search algorithm for principal/minor component analysis.
  • To unify normalized Hebbian and anti-Hebbian learning within a single framework.
  • To develop a multi-unit algorithm capable of extracting multiple robust eigenvectors.

Main Methods:

  • Development of a one-unit rule that is extended to a multi-unit algorithm.

Related Experiment Videos

  • Utilizing a general non-quadratic criterion where standard PCA/MCA emerge as special cases.
  • Mathematical analysis of the learning rule and verification through simulations.

    • Main Results:

    • The proposed algorithm successfully computes principal or minor component solutions.
    • It enables simultaneous extraction of several robust counterparts of principal/minor eigenvectors.
    • Theoretical analysis and simulation results confirm the algorithm's efficacy.

    Conclusions:

    • The bigradient approach offers a unified and robust method for eigenvector extraction.
    • The algorithm demonstrates potential for applications in blind source separation.
    • This work advances the field of unsupervised learning for signal processing.