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

Unsupervised learning in noise.

B Kosko1

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

IEEE Transactions on Neural Networks
|January 1, 1990
PubMed
Summary
This summary is machine-generated.

A novel differential competitive learning law utilizes neuronal signal velocity for reinforcement. This method enhances coding and stability in neural networks, demonstrated through RABAM systems and annealing models.

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

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

Differential competitive learning for centroid estimation and phoneme recognition.

IEEE transactions on neural networks·1991
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

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Dynamical Systems

Background:

  • Differential Hebbian learning systems are crucial for understanding neural network dynamics.
  • Existing models often lack efficient unsupervised reinforcement mechanisms.
  • The Gluck-Parker interpretation provides a framework for analyzing signal functions.

Purpose of the Study:

  • Introduce a new hybrid learning law: the differential competitive law.
  • Examine the coding and stability of this law in feedforward and feedback networks.
  • Extend the analysis to RABAM systems and annealing models.

Main Methods:

  • Utilizing neuronal signal velocity as a local unsupervised reinforcement mechanism.
  • Applying the Gluck-Parker pulse-coding interpretation for signal function analysis.

Related Experiment Videos

  • Summarizing second-order behavior of random adaptive bidirectional associative memory (RABAM) Brownian-diffusion systems.

    • Main Results:

    • The differential competitive law demonstrates effective coding and stability in neural networks.
    • The RABAM noise suppression theorem shows rapid exponential decrease in velocities.
    • The RABAM annealing model offers a unified framework for optimization and learning systems.

    Conclusions:

    • The differential competitive law presents a promising new approach for neural network learning.
    • The findings contribute to understanding noise suppression and optimization in complex systems.
    • This work unifies the analysis of Geman-Hwang optimization and Boltzmann machine learning.