Abstract
This paper presents a technique for making neural networks context-sensitive by using a symbolic context-management system to manage their weights. Instead of having a very large network that itself must take context into account, our approach uses one or more small networks whose weights are associated with symbolic representations of contexts an agent may encounter. When the context-management system determines what the current context is, it sets the networks’ weights appropriately for the context. This paper describes the approach and presents the results of experiments that show that our approach greatly reduces the training time of the networks as well as enhancing their performance.
This work was supported in part by the United States Office of Naval Research through grants N0001-14-96-1-5009 and N0001-14-98-1-0648. The content does not necessarily reflect the position or the policy of the U.S. government, and no official endorsement should be inferred.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Robert P. Arritt and Roy M. Turner. A system for context diagnosis. Technical Report 2003-1, University of Maine Computer Science Department, 2003.
D. Richard Blidberg, Roy M. Turner, and Steven G. Chappell. Autonomous underwater vehicles: Current activities and research opportunities. Robotics and Autonomous Systems, 7:139–150, 1991.
Don Brutzman, Mike Burns, Mike Campbell, Duane Davis, Tony Healey, Mike Holden, Brad Leonhardt, Dave Marco, Dave McClarin, Bob McGhee, and Russ Whales. NPS Phoenix AUV software integration and in-water testing. In Proceedings of the 1996 IEEE Symposium on Autonomous Underwater Vehicle Technology (AUV’96), pages 99–, Monterey, CA, USA, June 1996.
T.B. Curtin, J.G. Bellingham, J. Catipovic, and D. Webb. Autonomous oceanographic sampling networks. Oceanography, 6(3), 1993.
M. T. Hagan and M. Menha. Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6):989–993, 1994.
Simon Haykin. Neural Networks: A Comprehensive Foundation. Prentice-Hall Inc., 1999.
Amy E. Henninger, Avelino J. Gonzalez, Michael Georgiopoulos, and Ronald F. DeMara. A connectionist-symbolic approach to modeling agent behavior: Neural networks grouped by context. In Proceedings of the Third International and Interdisiplinary Conference on Modeling and Using Context, pages 198–209, 2001.
J.H. Lawton, R.M. Turner, and E.H. Turner. A unified long-term memory system. In Proceedings of the 1998 IEEE International Conference on Case-Based Reasoning, 1998.
Henrik Schmidt, James G. Bellingham, Mark Johnson, David Herold, David M. Farmer, and Richard Pawlowicz. Real-time frontal mapping with AUVs in a coastal environment. In Proceedings of the IEEE Oceanic Engineering Society Conference (OCEANS’96 MTS), pages 1094–1098, 1996.
Roy M. Turner. Intelligent control of autonomous underwater vehicles: The Orca project. In Proceedings of the 1995 IEEE International Conference on Systems, Man, and Cybernetics, 1995.
Roy M. Turner. Determining the context-dependent meaning of fuzzy subsets. In Proceedings of the First International and Interdisiplinary Conference on Modeling and Using Context, 1997.
Roy M. Turner. Context-mediated behavior for intelligent agents. International Journal of Human-Computer Studies, 48(3):307–330, March 1998.
Roy M. Turner. A model of explicit context representation and use for intelligent agents. In Proceedings of the Second International and Interdisiplinary Conference on Modeling and Using Context, 1999.
L. A. Zadeh. A theory of approximate reasoning. In J. Hayes, D. Michie, and L.I. Mikulich, editors, Machine Intelligence 9, pages 149–194. Halstead Press, 1979.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arritt, R.P., Turner, R.M. (2003). Context-Sensitive Weights for a Neural Network. In: Blackburn, P., Ghidini, C., Turner, R.M., Giunchiglia, F. (eds) Modeling and Using Context. CONTEXT 2003. Lecture Notes in Computer Science(), vol 2680. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44958-2_3
Download citation
DOI: https://doi.org/10.1007/3-540-44958-2_3
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40380-7
Online ISBN: 978-3-540-44958-4
eBook Packages: Springer Book Archive