Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Generalizing CMAC architecture and training.

F J González-Serrano¹, A R Figueiras-Vidal, A Artés-Rodríguez

¹DTC-ETSI Telecomunicación, Universidad de Vigo, As Lagoas-Marcosende, 36200 Vigo, Spain.

IEEE Transactions on Neural Networks

|February 8, 2008

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

Machine learning and data mining: strategies for hypothesis generation.

Molecular psychiatry·2012

Same author

Cost functions to estimate a posteriori probabilities in multiclass problems.

IEEE transactions on neural networks·2008

Same author

Sample selection via clustering to construct support vector-like classifiers.

IEEE transactions on neural networks·2008

Same author

On the structure of strict sense Bayesian cost functions and its applications.

IEEE transactions on neural networks·2008

Same author

Weighted least squares training of support vector classifiers leading to compact and adaptive schemes.

IEEE transactions on neural networks·2008

Same author

Empirical risk minimization for support vector classifiers.

IEEE transactions on neural networks·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 generalized Cerebellar Model Articulation Controller (GCMAC) to improve neural network accuracy and convergence speed for complex data. The GCMAC offers enhanced representation abilities for heterogeneous inputs.

Area of Science:

Artificial Intelligence
Machine Learning
Neural Networks

Background:

The Cerebellar Model Articulation Controller (CMAC) is a fast neural network utilizing local approximations.
Its fixed structure limits accuracy and convergence with diverse input data.

Purpose of the Study:

To propose a generalized CMAC (GCMAC) network addressing limitations of the standard CMAC.
To enhance approximation accuracy and convergence speed for heterogeneous inputs.

Main Methods:

Developed a GCMAC network allowing variable generalization degrees per input.
Analyzed GCMAC representation capabilities and derived output function constraints.
Introduced an adaptive network growing methodology.

Related Experiment Videos

Main Results:

The GCMAC demonstrates improved representation abilities compared to standard CMAC.
Simulated examples validate the effectiveness of the GCMAC approach and adaptive growing method.

Conclusions:

The proposed GCMAC offers a more flexible and accurate alternative to traditional CMAC networks.
The adaptive growing method further optimizes network performance for complex datasets.