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

Growing subspace pattern recognition methods and their neural-network models.

M Prakash1, M N Murty

  • 1Dept. of Comput. Sci. and Autom., Indian Inst. of Sci., Bangalore.

IEEE Transactions on Neural Networks
|January 1, 1997
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

Magnetic resonance neurography: part 2- interpretation decoded: a guide to Neuropathy Score Reporting and Data System and imaging signs for efficient diagnosis of peripheral nerve lesions.

Clinical radiology·2026
Same author

Magnetic Resonance Neurography (MRN): part 1- basic concepts, technical considerations, interpretation, and clinical utility.

Clinical radiology·2026
Same author

Survival Benefits Outweigh Germline Competition Costs in Kin Chimeras.

bioRxiv : the preprint server for biology·2026
Same author

An Advanced Mobile Laboratory to enable field-based microbial ecology and cell biology across scales.

bioRxiv : the preprint server for biology·2026
Same author

Quadratic mixed convection of Maxwell-Buongiorno nanofluid over cubic stratified surface incorporating cross diffusion effects and solar radiation.

Scientific reports·2025
Same author

Cleaner production of performance-enhanced hybrid composites using agro-industrial wastes: A sustainable waste management strategy.

Journal of environmental management·2025
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 new learning subspace methods (LSMs) for automatic feature extraction and classification. These improved algorithms enhance scalability and classification speed for complex pattern recognition tasks.

Area of Science:

  • Statistical Pattern Recognition
  • Machine Learning
  • Artificial Neural Networks

Background:

  • Feature selection in statistical pattern recognition often relies on human expertise, which can be inefficient and suboptimal.
  • Existing learning subspace methods (LSMs) offer potential for integrated feature extraction and classification but face limitations in determining cluster numbers and scalability.

Purpose of the Study:

  • To propose novel algorithms and neural network implementations for learning subspace methods (LSMs) to address limitations in automatic feature selection and classification.
  • To enhance the scalability and efficiency of LSMs for large-dimensional pattern recognition problems.

Main Methods:

  • Development of two new LSM algorithms with neural network implementations.
  • Introduction of a strategy to add and adapt clusters incrementally, eliminating trial-and-error for cluster number determination.

Related Experiment Videos

  • Integration with principal component analysis neural networks to improve scalability.

    • Main Results:

    • The proposed LSM classifiers demonstrate classification accuracy comparable to established methods like multilayer perceptrons and nearest-neighbor classifiers.
    • The new algorithms show significant improvements in classification speed and design scalability, particularly for high-dimensional datasets.

    Conclusions:

    • The novel LSM algorithms offer a more automated and efficient approach to feature extraction and classification in statistical pattern recognition.
    • These methods present a promising alternative to existing classifiers, especially for large-scale, complex pattern recognition challenges.