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 modified algorithm for generalized discriminant analysis.

Wenming Zheng1, Li Zhao, Cairong Zou

  • 1Engineering Research Center of Information Processing and Application, Southest University, Nanjing, Jiangsu 210096, People's Republic of China.

Neural Computation
|May 8, 2004
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

Epidemiology and Drug Resistance of Pulmonary Nocardiosis Among Tuberculosis-Suspected Patients in Guangzhou, China.

Infection and drug resistance·2025
Same author

A Novel ECG-Derived Respiration Method Combining Frequency-Domain Feature and Interacting Multiple Model Smoother.

IEEE transactions on bio-medical engineering·2022
Same author

[Effects of adding straw carbon source to root knot nematode diseased soil on soil microbial biomass and protozoa abundance].

Ying yong sheng tai xue bao = The journal of applied ecology·2013
Same author

Radiation enhancing effects with the combination of sanazole and irinotecan in hypoxic HeLa human cervical cancer cell line.

Journal of B.U.ON. : official journal of the Balkan Union of Oncology·2013
Same author

[The high expression of HPV31 and 52 L2 fusion protein in E. coli and detection of its immunogenicity].

Zhonghua shi yan he lin chuang bing du xue za zhi = Zhonghua shiyan he linchuang bingduxue zazhi = Chinese journal of experimental and clinical virology·2013
Same author

Down-regulation of EMP1 is associated with epithelial hyperplasia and metaplasia in nasal polyps.

Histopathology·2013
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

A new Modified Generalized Discriminant Analysis (MGDA) method improves upon Generalized Discriminant Analysis (GDA) by resolving degenerate eigenvalues. This enhancement optimizes discriminant ability for better performance in pattern recognition tasks.

Area of Science:

  • Machine Learning
  • Pattern Recognition
  • Computer Vision

Background:

  • Generalized Discriminant Analysis (GDA) extends Linear Discriminant Analysis (LDA) to nonlinear domains using the kernel trick.
  • Standard GDA algorithms can yield degenerate eigenvalues, compromising optimal discriminant ability.
  • Degenerate eigenvalues result in non-optimal eigenvectors, limiting classification performance.

Purpose of the Study:

  • To propose a Modified Generalized Discriminant Analysis (MGDA) algorithm to address the degenerate eigenvalue problem in GDA.
  • To enhance the discriminant ability of GDA by optimizing solutions in the degenerate subspace.
  • To achieve superior performance compared to existing GDA methods.

Main Methods:

  • The proposed Modified Generalized Discriminant Analysis (MGDA) method modifies the GDA algorithm to resolve degenerate eigenvalues.

Related Experiment Videos

  • MGDA identifies and optimizes solutions within the subspace spanned by degenerate eigenvectors.
  • The method focuses on maximizing between-class scatter in the identified subspace.

    • Main Results:

    • Theoretical analysis demonstrates the effectiveness of the MGDA method in resolving eigenvalue degeneracy.
    • Experimental results on the ORL face database show improved performance of MGDA over standard GDA.
    • MGDA achieved better discriminant ability by effectively handling degenerate eigenvectors.

    Conclusions:

    • The Modified Generalized Discriminant Analysis (MGDA) effectively overcomes the limitations of degenerate eigenvalues in GDA.
    • MGDA offers enhanced discriminant capability, leading to improved performance in classification tasks.
    • This modified approach provides a more optimal solution for nonlinear dimensionality reduction and pattern recognition.