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

Preintegration lateral inhibition enhances unsupervised learning.

M W Spratling1, M H Johnson

  • 1Centre for Brain and Cognitive Development, Birkbeck College, London WC1E 7JL, U.K. m.spratling@bbk.ac.uk

Neural Computation
|August 20, 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

Mutual gaze and later social attention development in infants at typical and elevated familial likelihood for ASD and/or ADHD.

Early human development·2025
Same author

Atypical Resting-State EEG Graph Metrics of Network Efficiency Across Development in Autism and Their Association with Social Cognition: Results from the LEAP Study.

Journal of autism and developmental disorders·2025
Same author

A Concurrent Validity Study of the Mullen Scales of Early Learning (MSEL) and the MacArthur-Bates Communicative Developmental Inventory (CDI) in Infants with an Elevated Likelihood or Diagnosis of Autism.

Journal of autism and developmental disorders·2025
Same author

Imaging Cerebral Energy Metabolism in Healthy Infants.

Advances in experimental medicine and biology·2022
Same author

Preference for biological motion is reduced in ASD: implications for clinical trials and the search for biomarkers.

Molecular autism·2021
Same author

The American Society of Neuroradiology: Cultivating a Diverse and Inclusive Culture to Build a Stronger Organization.

AJNR. American journal of neuroradiology·2021
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 neural network architecture using preintegration lateral inhibition, outperforming conventional models in generating accurate perceptual representations. This biologically plausible approach offers computational advantages for efficient learning.

Area of Science:

  • Computational neuroscience
  • Artificial intelligence
  • Machine learning

Background:

  • Conventional neural networks often employ postintegration lateral inhibition for competitive mechanisms.
  • These models can exhibit computational deficiencies, failing to generate appropriate perceptual representations in certain scenarios.

Purpose of the Study:

  • To propose and evaluate an alternative neural network architecture utilizing preintegration lateral inhibition.
  • To demonstrate the computational advantages and learning efficiency of this new architecture.
  • To ensure biological plausibility by aligning with neuroanatomical and neurophysiological data.

Main Methods:

  • Developed a novel neural network architecture where nodes compete for input reception (preintegration lateral inhibition).

Related Experiment Videos

  • Compared the performance of the new architecture against conventional models using postintegration lateral inhibition.
  • Assessed the ability to generate and learn appropriate perceptual representations.

    • Main Results:

    • The proposed architecture with preintegration lateral inhibition demonstrates superior coding properties.
    • This model efficiently learns appropriate perceptual representations.
    • The architecture shows consistency with existing neuroanatomical and neurophysiological findings.

    Conclusions:

    • Preintegration lateral inhibition offers significant computational advantages over postintegration lateral inhibition in neural networks.
    • The novel architecture is both computationally effective and biologically plausible.
    • This approach facilitates efficient learning of perceptual representations.