Title :
Learning convergence in the cerebellar model articulation controller
Author :
Wong, Yiu-Fai ; Sideris, Athanasios
Author_Institution :
Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA, USA
fDate :
1/1/1992 12:00:00 AM
Abstract :
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
Keywords :
controllers; learning systems; neural nets; robots; CMAC learning; cerebellar model articulation controller; computer simulation; inverse dynamics; learning algorithm; training data; two-link robot arm; Computer simulation; Convergence; Helium; Memory management; Neural networks; Robots; Space technology; Table lookup; Testing; Training data;
Journal_Title :
Neural Networks, IEEE Transactions on
