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

Representation and extrapolation in multilayer perceptrons.

Antony Browne1

  • 1School of Computing, Information Systems and Mathematics, London Guildhall University, London UK. abrowne@lgu.ac.uk

Neural Computation
|June 25, 2002
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

Detecting systematic structure in distributed representations.

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

Connectionist systems need to extrapolate for cognitive tasks. This study shows that how information is represented significantly impacts a system's ability to extrapolate, crucial for artificial intelligence development.

Area of Science:

  • Cognitive Science
  • Artificial Intelligence
  • Computational Neuroscience

Background:

  • Connectionist systems are crucial for explaining cognition and performing practical tasks.
  • Extrapolation is a key capability for these systems.

Purpose of the Study:

  • To investigate the relationship between input representation and extrapolation in connectionist systems.
  • To understand how different representations affect a system's ability to generalize beyond training data.

Main Methods:

  • Simulations of multilayer perceptrons were used.
  • Systems were trained to model the identity function.

Main Results:

  • Input representation was found to have a significant effect on extrapolation.

Related Experiment Videos

  • Specific representational choices markedly influence generalization capabilities.

    • Conclusions:

    • The way information is represented is a critical factor in the extrapolation performance of connectionist models.
    • Optimizing input representation is essential for developing more capable artificial intelligence systems.