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

Detecting systematic structure in distributed representations.

Antony Browne1

  • 1School of Information Systems, University College Northampton, Northampton, UK

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
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

The extraction of information and knowledge from trained neural networks.

Methods in molecular biology (Clifton, N.J.)·2008
Same author

Automatic relevance determination for identifying thalamic regions implicated in schizophrenia.

IEEE transactions on neural networks·2008
Same author

Representation and extrapolation in multilayer perceptrons.

Neural computation·2002
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

A new method analyzes systematic structure in feedforward neural networks by measuring inter-representational distances. This approach aids in understanding how networks unify distributed representations, offering an alternative to previous vector similarity techniques.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Understanding the internal structure of neural networks is crucial for interpretability.
  • Previous methods for analyzing network structure often rely on vector similarity.
  • Distributed representations are fundamental to modern neural network architectures.

Purpose of the Study:

  • To introduce a novel method for analyzing systematic structure within feedforward neural networks.
  • To apply this method to understand unification processes in distributed representations.
  • To provide an alternative approach for detecting systematic structure in neural networks.

Main Methods:

  • Developed a new analytical method focusing on inter-representational distances.

Related Experiment Videos

  • Applied the method to examine how feedforward neural networks perform unification.
  • Contrasted the distance-based approach with prior techniques that use vector similarities.

    • Main Results:

    • The novel method successfully detects systematic structure by analyzing distances between representations.
    • This technique offers insights into the unification mechanisms of distributed representations within networks.
    • The approach is shown to be effective for identifying systematicity.

    Conclusions:

    • The developed method provides a novel way to analyze systematic structure in feedforward neural networks.
    • Inter-representational distances offer a valuable metric for understanding network function and representation unification.
    • This technique has broader applicability for analyzing systematic structure in other networks utilizing distributed representations.