Learning convergence in the cerebellar model articulation controller

Learning convergence in the cerebellar model articulation controller

A new way to look at the learning algorithm in the cerebellar model articulation controller (CMAC) proposed by J.S. Albus (1975) is presented. A proof that the CMAC learning always converges with arbitrary accuracy on any set of training data is obtained. An alternative way to implement CMAC based o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on neural networks 1992-01, Vol.3 (1), p.115-121
Hauptverfasser: Wong, Y., Sideris, A.
Format: Artikel
Sprache:eng
Schlagworte:
Applied sciences
Computer Science
Computer Science, Artificial Intelligence
Computer Science, Hardware & Architecture
Computer Science, Theory & Methods
Computer science
control theory
systems
Computer simulation
Control theory. Systems
Convergence
Engineering
Engineering, Electrical & Electronic
Exact sciences and technology
Memory management
Neural networks
Robotics
Robots
Science & Technology
Space technology
Table lookup
Technology
Testing
Training data
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A new way to look at the learning algorithm in the cerebellar model articulation controller (CMAC) proposed by J.S. Albus (1975) is presented. A proof that the CMAC learning always converges with arbitrary accuracy on any set of training data is obtained. An alternative way to implement CMAC based on the insights obtained in the process is proposed. The scheme is tested with a computer simulation for learning the inverse dynamics of a two-link robot arm.< >
ISSN:1045-9227
1941-0093
DOI:10.1109/72.105424