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 self-organizing HCMAC neural-network classifier.

Hahn-Ming Lee1, Chih-Ming Chen, Yung-Feng Lu

  • 1Dept. of Comput. Sci. and Inf. Eng., Nat. Taiwan Univ. of Sci. and Technol., Taiwan.

IEEE Transactions on Neural Networks
|February 2, 2008
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

Entropy engineering in multimetallic hydroxides and oxides: a new paradigm for electrocatalytic oxygen evolution.

Nanoscale horizons·2026
Same author

From prediction to materials design: machine learning in electrocatalytic water splitting.

Chemical communications (Cambridge, England)·2026
Same author

Asymmetric Total Synthesis of C2-OH Lycopodium Alkaloids (-)-Palhinine B, (-)-Palhinine C, and (+)-Palhinine B Enabled by Stereocontrolled Diels-Alder Strategy.

Organic letters·2026
Same author

Emergence of outbreak-driving high-risk <i>Pseudomonas aeruginosa</i> lineages in Taiwan: phylogenomic insights into ST292 and the ST235* sublineage.

Microbial genomics·2026
Same author

Sodium-Glucose Cotransporter-2 Inhibitors and Cardiorenal Events in Nonalbuminuric Kidney Disease.

Kidney international reports·2026
Same author

Rescuing Neurodevelopmental Deficits in AMPA Receptor Gain-of-Function Mutant.

bioRxiv : the preprint server for biology·2026
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a self-organizing hierarchical cerebellar model arithmetic computer (HCMAC) neural network for improved high-dimensional classification. The novel approach enhances learning speed and reduces memory needs compared to conventional CMAC methods.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Conventional Cerebellar Model Arithmetic Computer (CMAC) networks offer fast learning and generalization but require significant memory for high-dimensional problems.
  • CMAC performance is sensitive to input space quantization, often requiring extensive parameter tuning.
  • Existing methods struggle with efficient memory allocation and input space discretization in complex classification tasks.

Purpose of the Study:

  • To present a novel self-organizing hierarchical cerebellar model arithmetic computer (HCMAC) neural network classifier.
  • To address the memory and input space quantization challenges of conventional CMAC in high-dimensional classification.
  • To develop an automated method for input space quantization using data distribution.

Main Methods:

Related Experiment Videos

  • Implementation of a self-organizing input space module integrated with an HCMAC neural network.
  • Utilizing Shannon's entropy measure and golden-section search for automated input space quantization.
  • Supervised learning approach applied to the HCMAC for classification tasks.

Main Results:

  • The self-organizing HCMAC demonstrates fast learning capabilities and reduced memory requirements.
  • Experimental results show superior performance over conventional CMAC for high-dimensional classification problems.
  • The proposed classifier exhibits enhanced classification ability compared to other benchmark classifiers.

Conclusions:

  • The self-organizing HCMAC effectively resolves high-dimensional classification problems with improved efficiency.
  • The automated input space module simplifies parameter searching and optimizes memory allocation.
  • This novel HCMAC architecture offers a promising solution for complex classification tasks in machine learning.