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

Codeword distribution for frequency sensitive competitive learning with one-dimensional input data.

A S Galanopoulos1, S C Ahalt

  • 1Dept. of Electr. Eng., Ohio State Univ., Columbus, OH.

IEEE Transactions on Neural Networks
|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

Optical implementation and applications of closest-vector selection in neural networks.

Applied optics·2010
Same author

Diffusion approximation of frequency sensitive competitive learning.

IEEE transactions on neural networks·1997
Same author

Acoustic-to-phonetic mapping using recurrent neural networks.

IEEE transactions on neural networks·1994
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 analyzes the codeword distribution of frequency sensitive competitive learning (FSCL). We found its density follows a power law, adaptable for minimizing various distortion measures.

Area of Science:

  • Machine Learning
  • Computational Neuroscience
  • Data Analysis

Background:

  • Competitive learning algorithms are crucial for data analysis and pattern recognition.
  • Frequency Sensitive Competitive Learning (FSCL) is a specific type of competitive learning algorithm.
  • Understanding codeword distribution is key to optimizing algorithm performance.

Purpose of the Study:

  • To investigate the codeword distribution of the FSCL algorithm with one-dimensional input data.
  • To determine the asymptotic behavior of codeword density for FSCL.
  • To explore the adaptability of FSCL for different distortion measures.

Main Methods:

  • Theoretical analysis of the FSCL algorithm.
  • Derivation of the asymptotic codeword density.

Related Experiment Videos

  • Mathematical formulation of the power law relationship Q(x)=C.P(x)(alpha).
  • Investigation of L(p) distortion measure minimization.

    • Main Results:

    • The asymptotic codeword density of FSCL follows a power law: Q(x)=C.P(x)(alpha).
    • The exponent alpha is dependent on the algorithm's specifics and the chosen distortion measure.
    • FSCL can be modified to minimize L(p) distortion measures for p in the range (0,2].

    Conclusions:

    • The study provides a theoretical framework for understanding FSCL's codeword distribution.
    • The findings highlight FSCL's flexibility in adapting to various data minimization objectives.
    • This research contributes to the theoretical underpinnings of competitive learning algorithms.