Abstract
This paper describes a neural-based artificial system, called Paramount, for learning, storing, and reproducing parameterized motor sequences, i.e. temporal sequences consisting of motor commands as sequence elements. Paramount is designed to control the arm of a robot, mimicking the functionality of specific parts of the human motor system up to a certain extent. After having been trained with a number of sample sequences, Paramount is not only able to recall these sequences exactly as they were learned, but also to generalize slightly modified (scaled) versions according to a set of parameters.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Albus, J. S.: A new approach to manipulator control: The cerebellar model articulation controller (CMAC). Transactions ASME (1975)
Ans, B., Coiton, Y., Gilhodes, J.-C, Velay, J.-L.: A Neural Network Model for Temporal Sequence Learning and Motor Programming. Neural Networks (Elsevier Science) 7(9) (1994) 1461–1476
Elman, J.: Finding structure in time. Cognitive Science 14 (1990) 179–211
Ersü, E., Tolle, H.: Hierarchical learning control — an approach with neuron-like associative memories. In IEEE Conference on Neural Information Processing Systems — Natural and Synthetic, Denver, CO (1987) pp. 249–261
Hohm, K., Felzer, T., Marenbach, P.: Parameterized temporal sequences for motor control of a robot system. MSCA'96, Crete, Greece (1996)
Jordan, M. I.: Attractor dynamics and parallelism in a connectionist sequential machine. In Proccedings of the Eighth Annual Conference of the Cognitive Science Society, Hillsdale, NJ (1986) pp. 531–546
Mischo, W. S.: How to adapt in neurocontrol: A decision for CMAC. In Zbikowsky, R., Hunt, K. J. (Eds.), Neural Adaptive Control Theory. World Scientific (1996)
Mozer, M. C.: The induction of multiscale temporal structure. In Moody, J. E., Hanson, S. J., Lippmann, R. P. (Eds.), Advances in Neural Information Processing Systems 4 (1992) pp. 275–282. San Mateo, CA: Morgan Kaufmann.
Mozer, M. C.: Neural net architectures for temporal sequence processing. In Weigend, A. S., Gershenfeld, N. A. (Eds.), Time series prediction: Forecasting the future and understanding the past, Reading, MA: Addison-Wesley (1993)
Rumelhart, D. E., Hinton, G. E., Williams R. J.: Learning internal representations by error propagation. In Rumelhart, D. E., McClelland, J. L. (Eds.), Parallel Distributed Processing: Explorations in the Microstructures of Cognition, Volume 1 (1986) pp. 318–362. Cambridge, MA: MIT Press
Schmidt, R. A.: Motor control and learning: A behavioral emphasis. Champaign, Ill.: Human Kinetics Publishers (1982)
v. d. Smagt, P.: Simderella: a robot simulator for neuro-controller design. Neurocomputing (Elsevier Science) 6(2) (1994)s
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Felzer, T., Hartmann, P., Hohm, K., Marenbach, P. (1997). Motor sequence processing with an artificial learning system. In: Mira, J., Moreno-DÃaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032591
Download citation
DOI: https://doi.org/10.1007/BFb0032591
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive