Robotic system sensitivity to neural network learning rate: Theory, simulation, and experiments

International Journal of Robotics Research

Volumn 19, Issue 10, 2000, Pages 955-968

  Clark, Christopher M ^a   Mills, James K ^a  

^a UNIVERSITY OF TORONTO   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; COMPUTER SIMULATION; ITERATIVE METHODS; NEURAL NETWORKS; SENSITIVITY ANALYSIS;

NEURAL NETWORK CONTROLLERS;

ROBOT LEARNING;

EID: 0034294457     PISSN: 02783649     EISSN: None     Source Type: Journal    
DOI: 10.1177/02783640022067887     Document Type: Article

References (12)

1. Albus, J. S. 1975. A new approach to manipulator control: Cerebellar model articulation controller (CMAC). Trans. ASME J. Dynamic Systems, Measurement and Control, September, pp. 220-223.
2. Chen, P.C.Y., Mills, J. K., and Smith, K. C. 1996. Performance improvement of robot continuous-path operation through iterative learning using neural networks. Machine Learning Journal 23:191-220.
3. Chen, P.C.Y., Ogilvie, A., Clark, C., Zhou, K., and Mills, J. K. 1998. Development of a neural network module for improving the performance of a commercial robot. World Automation Conference, Alaska, May, pp. 288-293.
4. Frank, W. P. 1976. Introduction to Sensitivity Theory. San Diego: Academic Press.
5. Graham, D.P.W., and D'Eleuterio, G.M.T. 1990. MOVE -A neural network paradigm for robotic control. 6th CASI Conference on Astronautics, Ottawa, Canada, October 21, pp. 588-593.
6. Graham, D.P.W., and D'Eleuterio, G.M.T. 1991. Robotic control using a modular architecture of cooperative artificial neural networks. In Artificial Neural Networks, vol. 1, ed. T. Kohonen, 365-370. Amsterdam: North Holland.
7. Haykin, S. 1994. Neural Networks: A Comprehensive Foundation. Englewood Cliffs, NJ: Macmillan College.
8. Jacobs, R., and Jordan, M. I. 1993. Learning piecewise control strategies in a modular neural network architecture. IEEE Transactions on Systems, Man, and Cybernetics 23(2):337-345.
9. Jacobs, R., Jordan, M. I., Nowlan, S. J., and Hinton, G.E. 1991. Adaptive mixtures of local experts. Neural Computation 3(1):79-87.
10. Liu, H. T., and Mills, J. K. 1998. ROBOTOOL: A simulation software for robot performance analysis. Proceedings of the Canadian Society for Mechanical Engineering Forum, Toronto, Ontario, June, pp. 1044-1049.
11. Rueckl, J. G., Cave, K. R., and Kosslyn, S. M. 1989. Why and "what" and "where" processed by separate cortical visual systems? A computational investigation. Journal of Cognitive Neuroscience 1:171-186.
12. Rumelhart, D. E., Hinton, G. E., and Williams, R. J. 1986. Learning representations by back-propagating error. Nature (London) 323:533-536.