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

Hierarchically clustered adaptive quantization CMAC and its learning convergence.

S D Teddy1, E M K Lai, C Quek

  • 1School of Computer Engineering, Nanyang Technological University, Singapore 639798, Singapore.

IEEE Transactions on Neural Networks
|December 7, 2007
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

A novel cognitive interpretation of breast cancer thermography with complementary learning fuzzy neural memory structure.

Expert systems with applications·2020
Same author

Financial volatility trading using a self-organising neural-fuzzy semantic network and option straddle-based approach.

Expert systems with applications·2020
Same author

PSECMAC intelligent insulin schedule for diabetic blood glucose management under nonmeal announcement.

IEEE transactions on neural networks·2010
Same author

DCT-Yager FNN: a novel Yager-based fuzzy neural network with the discrete clustering technique.

IEEE transactions on neural networks·2008
Same author

PSECMAC: a novel self-organizing multiresolution associative memory architecture.

IEEE transactions on neural networks·2008
Same author

POPFNN-AAR(S): a pseudo outer-product based fuzzy neural network.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
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 novel Hierarchically Clustered Adaptive Quantization CMAC (HCAQ-CMAC) to overcome limitations in standard CMAC neural networks. The HCAQ-CMAC improves memory efficiency and accuracy by nonuniformly quantizing input spaces, outperforming existing models in real-world applications.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • The Cerebellar Model Articulation Controller (CMAC) neural network is a computational model of the human cerebellum.
  • Uniform quantization in CMAC leads to constant output resolution, a generalization-accuracy dilemma, and inefficient memory usage, especially with high-dimensional inputs.
  • Existing nonuniform quantization methods for CMAC present a trade-off between memory efficiency and computational complexity.

Purpose of the Study:

  • To propose a novel CMAC architecture, the Hierarchically Clustered Adaptive Quantization CMAC (HCAQ-CMAC), inspired by brain organization.
  • To address the limitations of uniform quantization in CMAC, specifically improving memory utilization and output resolution.
  • To theoretically guarantee the learning convergence and stability of the proposed HCAQ-CMAC network.

Related Experiment Videos

Main Methods:

  • Employed hierarchical clustering for nonuniform input space quantization in the HCAQ-CMAC.
  • Identified significant input segments to allocate memory cells more effectively.
  • Proved the learning convergence and stability of the HCAQ-CMAC network.
  • Benchmarked HCAQ-CMAC against original CMAC and other variants on car maneuver control and blood glucose modeling.

Main Results:

  • The HCAQ-CMAC demonstrated an efficient memory allocation scheme.
  • The proposed network showed improved generalization and accuracy compared to existing CMAC variants.
  • HCAQ-CMAC achieved better or comparable performance with significantly smaller memory footprints.

Conclusions:

  • The HCAQ-CMAC effectively addresses the memory utilization and performance limitations of traditional CMAC networks.
  • Hierarchical clustering provides an efficient method for nonuniform input space quantization in CMAC.
  • The HCAQ-CMAC offers a promising alternative for applications requiring accurate and memory-efficient cerebellar modeling.