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

Constructing a query-able radial basis function artificial neural network.

Marijke F Augusteijn1, Kelly A Shaw

  • 1University of Colorado, Colorado Springs, USA. mfa@cs.uccs.edu

International Journal of Neural Systems
|October 9, 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

Prevalence of Autism Spectrum Disorder Severity Levels From the Fifth Edition of the Diagnostic and Statistical Manual (DSM-5) in the Autism and Developmental Disabilities Monitoring Network.

Journal of autism and developmental disorders·2026
Same author

Mortality Among Youth and Young Adults With Autism Spectrum Disorder, Intellectual Disability, or Cerebral Palsy.

JAMA pediatrics·2026
Same author

The effect of heel elevation on the stiffness gradient index of the digital flexor tendons in the equine forelimb of clinically normal horses.

Frontiers in veterinary science·2025
Same author

Prevalence and Early Identification of Autism Spectrum Disorder Among Children Aged 4 and 8 Years - Autism and Developmental Disabilities Monitoring Network, 16 Sites, United States, 2022.

Morbidity and mortality weekly report. Surveillance summaries (Washington, D.C. : 2002)·2025
Same author

Social vulnerability and the prevalence of autism spectrum disorder among 8-year-old children, Autism and Developmental Disabilities Monitoring Network, 2020.

Annals of epidemiology·2025
Same author

Community testing practices for autism within the autism and developmental disabilities monitoring network.

Paediatric and perinatal epidemiology·2024
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study introduces NetQuery, an explanation mechanism for Radial Basis Function (RBF) networks. NetQuery enhances RBF network interpretability by extracting meaningful "Why?" and "How can I...?" explanations, improving their acceptance as engineering tools.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Artificial neural networks (ANNs) often lack transparency, hindering their adoption as standard engineering tools.
  • Radial Basis Function (RBF) networks offer potential for explanation due to their locally tuned units.
  • Existing RBF networks can be opaque, making their decision-making processes difficult to understand.

Purpose of the Study:

  • To develop NetQuery, an explanation mechanism for trained Radial Basis Function networks.
  • To enhance the interpretability and transparency of RBF network reasoning.
  • To facilitate the use of RBF networks in practical engineering applications.

Main Methods:

  • Modification of standard RBF networks to identify input dependencies and enable sparse connectivity.

Related Experiment Videos

  • Implementation of an easily interpretable output layer within the RBF network architecture.
  • Development of a run-time pruning algorithm to simplify explanation extraction.
  • Querying the network for "Why?", "Why not?", and "How can I...?" explanations.

    • Main Results:

    • NetQuery successfully extracts meaningful "Why?" and "Why not?" explanations based on excitatory and inhibitory inputs and their linear relationships.
    • The extracted explanations were validated by creating a functional expert system.
    • NetQuery can provide "How can I...?" queries, aiding in pattern set quality analysis and suggesting category changes.

    Conclusions:

    • NetQuery significantly improves the interpretability of Radial Basis Function networks.
    • The developed explanation mechanism increases the potential for wider acceptance of RBF networks in engineering.
    • NetQuery offers valuable insights for understanding and improving data patterns.