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

Robust and fast learning for fuzzy cerebellar model articulation controllers.

Shun-Feng Su, Zne-Jung Lee, Yan-Ping Wang

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society

|February 14, 2006

Summary

This study enhances cerebellar model articulation controllers (CMAC) for faster, robust online learning. By integrating M-estimators and annealing, CMAC algorithms effectively handle noisy data and improve control performance.

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

Harpagide attenuates cerebral ischemic injury by modulating mitochondrial calcium homeostasis associated with the AMPK-MCU axis.

Scientific reports·2026

Same author

[Characteristics of nitrite-dependent anaerobic methane oxidation activity and microbial community in paddy fields under different fertilization treatments].

Ying yong sheng tai xue bao = The journal of applied ecology·2026

Same author

[Spatiotemporal pattern of the endangered <i>Hainania trichosperma</i> population in a karst seasonal rainforest of Guangxi, Southwest China].

Ying yong sheng tai xue bao = The journal of applied ecology·2026

Same author

Fragment-based discovery of pyrazole-5-carboxamide derivatives as ALK inhibitors against non-small cell lung cancer.

Bioorganic chemistry·2026

Same author

Corrigendum to "Quercetin attenuates cisplatin-induced mitochondrial apoptosis via PI3K/Akt mediated inhibition of oxidative stress in pericytes and improves the blood labyrinth barrier permeability" [Chemico-Biological Interactions 393 (2024) 110939].

Chemico-biological interactions·2026

Same author

Microbial community succession of cow manure and tobacco straw composting.

Frontiers in microbiomes·2026

Area of Science:

Robotics
Machine Learning
Control Systems

Background:

Cerebellar Model Articulation Controllers (CMAC) are widely used for adaptive control.
Traditional CMAC algorithms can be sensitive to outliers in training data.
Enhancing online learning and robustness is crucial for real-world applications.

Purpose of the Study:

To improve the online learning capability and robustness of CMAC algorithms.
To develop a CMAC approach that effectively handles outliers in training data.
To enhance the learning speed of fuzzy CMAC through credit assignment.

Main Methods:

Embedding M-estimators into CMAC learning algorithms to achieve robustness against outliers.
Adopting an annealing schedule for the learning constant to ensure robust learning.

Related Experiment Videos

Extending previous work on credit assignment for faster fuzzy CMAC learning.

Main Results:

The proposed CMAC algorithm demonstrates significantly faster and more robust learning compared to traditional methods.
Simulation examples confirm the effectiveness of the enhanced CMAC in handling noisy data.
The integration of a tuning parameter facilitates both online learning and fine-tuning.

Conclusions:

The developed CMAC approach offers superior performance in terms of learning speed and robustness.
The proposed method is effective for online learning control schemes, particularly in the presence of data outliers.
The findings pave the way for more reliable and efficient adaptive control systems.