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

Basis function models of the CMAC network.

A Kolcz1, Nigel M. Allinson

  • 1ECE Department, University of Colorado at Colorado Springs, 1420 Austin Bluffs Pkwy., Colorado Springs, USA

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

N-tuple network, CART and bagging.

Neural computation·2000
Same author

N-tuple Regression Network.

Neural networks : the official journal of the International Neural Network Society·1996
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

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

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

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

The Cerebellar Model Articulation Controller (CMAC) is interpreted as a General Memory Neural Network (GMNN). This provides a new basis function model for CMAC, offering insights into its performance and mapping capabilities.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • The Cerebellar Model Articulation Controller (CMAC) is a widely used neural network architecture.
  • Existing interpretations often focus on its direct application rather than its foundational structure.
  • Understanding CMAC within broader neural network frameworks can enhance its theoretical basis.

Purpose of the Study:

  • To interpret the Cerebellar Model Articulation Controller (CMAC) network within the General Memory Neural Network (GMNN) architecture.
  • To present CMAC as a specific type of basis function network.
  • To derive an average basis function form for CMAC based on its input quantization.

Main Methods:

  • Interpreting CMAC within the General Memory Neural Network (GMNN) formalism.

Related Experiment Videos

  • Analyzing CMAC's input quantization to define its basis function characteristics.
  • Developing basis-function models to represent CMAC mappings.
  • Utilizing numerical simulations to support the theoretical developments.

    • Main Results:

    • CMAC is successfully framed as a specific instance of a basis function network within the GMNN architecture.
    • A generalized, average basis function form for CMAC was derived.
    • The derived basis form enables the creation of basis-function models for CMAC.
    • These models offer enhanced insight into CMAC's mapping properties and performance.

    Conclusions:

    • The GMNN framework provides a valuable perspective for understanding CMAC.
    • The derived average basis function offers a new tool for analyzing and modeling CMAC.
    • This approach deepens the theoretical understanding of CMAC's internal workings and predictive capabilities.