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

Introducing asymmetry into interneuron learning

C Fyfe1

  • 1Department of Computer Science, University of Strathclyde, Glasgow, Scotland.

Neural Computation
|November 1, 1995
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

Dietary carbohydrate rather than protein intake drives colonic microbial fermentation during weight loss.

European journal of nutrition·2018
Same author

Antibacterial activity of eravacycline (TP-434), a novel fluorocycline, against hospital and community pathogens.

Antimicrobial agents and chemotherapy·2013
Same author

A randomized crossover study to assess the effect of an oat-rich diet on glycaemic control, plasma lipids and postprandial glycaemia, inflammation and oxidative stress in Type 2 diabetes.

Diabetic medicine : a journal of the British Diabetic Association·2013
Same author

The combined use of self-organizing maps and Andrews' Curves.

International journal of neural systems·2005
Same author

A neural implementation of canonical correlation analysis.

Neural networks : the official journal of the International Neural Network Society·2003
Same author

Kernel and nonlinear canonical correlation analysis.

International journal of neural systems·2001
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

This study introduces a novel artificial neural network that self-organizes using Hebbian learning and negative feedback. The network efficiently converges to principal components without needing weight clipping or normalization.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Artificial neural networks (ANNs) are powerful tools for data analysis.
  • Principal Component Analysis (PCA) is a fundamental technique for dimensionality reduction.
  • Existing ANNs often require complex training procedures, including weight normalization and decay.

Purpose of the Study:

  • To introduce a novel ANN architecture.
  • To demonstrate weight convergence to the principal component subspace.
  • To explore a self-organizing learning mechanism using Hebbian learning and negative feedback.

Main Methods:

  • A new ANN architecture is proposed.
  • The network utilizes simple Hebbian learning rules.

Related Experiment Videos

  • Negative feedback from interneurons to input neurons drives self-organization.
  • Asymmetry is introduced via interneuron-to-interneuron feedback for convergence to principal components.

    • Main Results:

    • The proposed ANN architecture demonstrates convergence to the principal component subspace.
    • The learning process relies solely on simple Hebbian learning.
    • The network achieves convergence without requiring weight clipping, normalization, or weight decay.
    • Simulations and theoretical analysis confirm the convergence properties.

    Conclusions:

    • The novel ANN architecture offers an efficient and self-organizing approach to principal component extraction.
    • Hebbian learning combined with specific negative feedback mechanisms provides a robust learning rule.
    • This architecture presents a simplified yet effective alternative to traditional PCA methods in ANNs.