Abstract
It has been suggested that inverse models serve feedforward controllers in the human brain. We have proposed a novel learning scheme to acquire a neural inverse model of a controlled object. This scheme propagates error “forward” in a multi-layered neural network to solve a credit assignment problem based on Newton-like method. In this paper, we apply a RLS algorithm to this scheme for the stability of learning. The suitability of the proposed scheme was confirmed by computer simulation; it could acquire an inverse dynamics model of a 2-link arm faster than a conventional scheme based on a back-propagation rule.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by backpropagation errors. Nature 323, 533–536 (1986)
Nagasawa, K., Fukumura, N., Uno, Y.: A forward-propagation rule for acquiring inverse models in multi-layered neural networks. IEICE Transactions, J85-D-II, 1066-1074 (2002) (in Japanese)
Ortega, J.M., Rheinboldt, W.C.: Iterative solution of nonlinear equations in several variables. Academic Press, New York (1970)
Heykin, S.: Adaptive filter theory, 3rd edn. Prentice Hall, Englewood Cliff (1996)
Kawato, M.: Feedback-error-learning neural network for supervised motor learning. In: Eckmiller, R. (ed.) Advanced Neural Computers, pp. 365–372. North Holland, Amsterdam (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ohama, Y., Fukumura, N., Uno, Y. (2004). A Forward-Propagation Rule for Acquiring Neural Inverse Models Using a RLS Algorithm. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds) Neural Information Processing. ICONIP 2004. Lecture Notes in Computer Science, vol 3316. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30499-9_90
Download citation
DOI: https://doi.org/10.1007/978-3-540-30499-9_90
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23931-4
Online ISBN: 978-3-540-30499-9
eBook Packages: Springer Book Archive