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

A memory-based self-generated basis function neural network.

C S Lin1, C K Li

  • 1Department of Electrical Engineering, University of Missouri-Columbia, MO 65211, USA. lin@ece.missouri.edu

International Journal of Neural Systems
|July 13, 1999
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

Precise Measurement of the Chromoelectric Dipole Moment of the Charm Quark.

Physical review letters·2026
Same author

Precise Measurement of Matter-Antimatter Asymmetry with Entangled Hyperon-Antihyperon Pairs.

Physical review letters·2026
Same author

Observation of Λ[over ¯]p→K^{+}π^{+}π^{-}π^{0} and Λ[over ¯]p→K^{+}π^{+}π^{-}2π^{0}.

Physical review letters·2026
Same author

First Measurement of the D_{s}^{+}→K^{0}μ^{+}ν_{μ} Decay.

Physical review letters·2026
Same author

Observation of the Electromagnetic Radiative Decays of the Λ(1520) and Λ(1690) to γΣ^{0}.

Physical review letters·2026
Same author

Observation of a Threshold Enhancement in the π^{+}π^{-} Spectrum in ψ(3686)→π^{+}π^{-}J/ψ Decays.

Physical review letters·2026
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 a novel Self-Generated Basis Function Neural Network (SGBFN) using Cerebellar Model Articulation Controllers (CMACs). The SGBFN offers reduced memory usage and faster learning convergence for complex modeling tasks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Conventional Cerebellar Model Articulation Controllers (CMACs) can be memory-intensive.
  • Multilayer neural networks may exhibit slower learning convergence.
  • High-dimensional modeling presents challenges for traditional neural network architectures.

Purpose of the Study:

  • To present a novel memory-efficient neural network architecture.
  • To improve learning convergence properties compared to existing methods.
  • To reduce memory footprint in high-dimensional data modeling.

Main Methods:

  • Development of a Self-Generated Basis Function Neural Network (SGBFN) architecture.
  • Composition of the SGBFN using smaller, specialized CMAC units.

Related Experiment Videos

  • Implementation of submodules where CMACs process input subsets, with submodule output as a product of CMAC outputs.
  • Network output as a sum of submodule outputs, with basis functions generated during learning.

    • Main Results:

    • The SGBFN demonstrates significantly reduced memory space requirements compared to conventional CMACs.
    • The novel structure achieves superior learning convergence properties.
    • For a given memory size, the SGBFN yields a smaller learning error than traditional CMACs.
    • Utilizing input subsets within CMACs effectively mitigates memory demands in high-dimensional scenarios.

    Conclusions:

    • The proposed SGBFN architecture offers a memory-efficient and effective alternative for neural network modeling.
    • The SGBFN's design facilitates faster learning and improved accuracy, particularly in high-dimensional spaces.
    • This novel approach holds promise for applications requiring substantial data processing with limited memory resources.