Data Storage in the Cerebellar Model Articulation Controller (CMAC)

  title={Data Storage in the Cerebellar Model Articulation Controller (CMAC)},
  author={James S. Albus},
  journal={Journal of Dynamic Systems Measurement and Control-transactions of The Asme},
  • J. Albus
  • Published 1 September 1975
  • Computer Science
  • Journal of Dynamic Systems Measurement and Control-transactions of The Asme
Development of a Recurrent Fuzzy CMAC With Adjustable Input Space Quantization and Self-Tuning Learning Rate for Control of a Dual-Axis Piezoelectric Actuated Micromotion Stage
Experimental results show that the proposed RFCMAC is feasible, and its performance is superior to that of the conventional CMAC control scheme.
A hybrid maximum error algorithm with neighborhood training for CMAC
  • S. Sayil, Kwang Y. Lee
  • Computer Science
    Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)
  • 2002
A hybrid approach has been developed for the maximum error algorithm by using the neighborhood training technique for the initial training period and yielded faster initial convergence which is very important for many control applications.
Cerebellar learning of internal models for reaching and grasping: adaptive control in the presence of delays
It is argued that with trajectory deviations detected at the spinal cord level, eligibility traces in the cerebellum can solve the temporal mismatch problem of delayed error signals and implement a nonlinear predictive regulator by learning part of the inverse dynamics of the plant and spinal circuit.
Biologically Inspired Spatial Representation
This thesis explores a biologically inspired method of encoding continuous space within a population of neurons and provides an example of how insights regarding how the brain may encode information can inspire new ways of designing artificial neural networks.
Systèmes cognitifs artificiels : du concept au développement de comportements intelligents en robotique autonome. (Artificial cognitive systems: from concept to the development of intelligent behaviours in autonomous robotics)
La cognition associee au robot est donc le resultat d’un processus de developpement par lequel le robot devient progressivement plus habile and acquiert les connaissances lui permettant d‘interpreter le monde qui l’entoure.
Hierarchical Reinforcement Learning with Function Approximation for Adaptive Control
This dissertation investigates the incorporation of function approximation and hierarchy into reinforcement learning for use in an adaptive control setting through empirical studies and the use of abstraction and changes in task representation are examined.
Robust CMAC control schemes for dynamic trajectory following
The improved CMAC learning approach under the robust control structure, using the concept of credit assignment, will be employed to determine control variables that can trace other states repeatedly during control processes.
Implementation of a Variable D-H Parameter Model for Robot Calibration Using an FCMAC Learning Algorithm
A variable D-H (Denavit and Hartenberg) parameter model is proposed to formulate variations of calibrated error parameters (CEPs) that vary in different regions of the robot workspace.