Jove
Visualize
Contact Us

Related Experiment Videos

Differential competitive learning for centroid estimation and phoneme recognition.

S G Kong1, B Kosko

  • 1Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA.

IEEE Transactions on Neural Networks
|January 1, 1991
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

Adaptive bidirectional associative memories.

Applied optics·2010
Same author

Block-based neural networks.

IEEE transactions on neural networks·2008
Same author

Robust stochastic resonance: signal detection and adaptation in impulsive noise.

Physical review. E, Statistical, nonlinear, and soft matter physics·2001
Same author

Fuzzy function approximation with ellipsoidal rules.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·1996
Same author

Adaptive fuzzy systems for backing up a truck-and-trailer.

IEEE transactions on neural networks·1992
Same author

Stochastic competitive learning.

IEEE transactions on neural networks·1991
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
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

Differential-competitive-learning (DCL) offers unsupervised adaptive vector quantization, outperforming supervised methods in centroid estimation and phoneme recognition by utilizing signal-velocity for reinforcement, leading to faster convergence and improved accuracy.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Signal Processing

Background:

  • Supervised competitive learning (SCL) systems require neurons to win competitions for activation.
  • Standard SCL systems do not utilize instantaneous win-rate information for learning.
  • Adaptive vector quantization is crucial for pattern recognition and probability density estimation.

Purpose of the Study:

  • To compare the efficacy of a differential-competitive-learning (DCL) system against two supervised competitive-learning (SCL) systems.
  • To evaluate performance in centroid estimation and phoneme recognition tasks.
  • To demonstrate the unsupervised learning capabilities of DCL.

Main Methods:

  • Implemented a differential-competitive-learning (DCL) system.

Related Experiment Videos

  • Compared DCL with two supervised competitive-learning (SCL) systems.
  • Utilized signal-velocity information for unsupervised local reinforcement in DCL.
  • Employed synaptic fan-in vectors for adaptive quantization of pattern space.

    • Main Results:

    • Unsupervised DCL-trained synaptic vectors demonstrated faster convergence to class centroids compared to SCL.
    • DCL-trained vectors exhibited less wandering around centroids than SCL-trained vectors.
    • DCL showed superior classification accuracy for English phonemes over SCL.

    Conclusions:

    • Differential-competitive-learning (DCL) provides an effective unsupervised approach for adaptive vector quantization.
    • DCL surpasses SCL in both convergence speed and stability for centroid estimation.
    • DCL offers enhanced classification accuracy, particularly in tasks like phoneme recognition.