Abstract
In this paper, two neural network mechanisms for synthesis of solutions in non-conflict cases in distributed expert systems (DESs) are proposed. The ideas are: inputs of the neural network are different solutions for the same problem from different expert systems in DESs; outputs of the neural network are the final solutions for the problem after combining different solutions which should be the same as the human experts' final solutions. The first point is to set up the architecture of the neural network and train the neural network by adjusting weights of links to match the outputs of the neural network against the human experts' solutions for all patterns. The second point is that the neural network mechanism proposed in this paper can accommodate the variable number of inputs and outputs without changing neural network architecture.
This research was supported by a large grant from the Australian Research Council (A49530850).
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
R. Duda, P. Hart and N. Nilsson (1976). Subjective Bayesian Method for Rule-based Inference System, AFIPS, 45, pp. 1075–1082.
N. A. Khan and R. Jain (1985). Uncertainty Management in a Distributed Knowledge Based System. In Proceedings of 5th International Joint Conference on Artificial Intelligence, Los Angeles, pp. 318–320.
D. Liu, F. Zheng, Z. Ma and Q. Shi (1992). Conflict Resolution in Multi-ES cooperation Systems. Journal of Computer Science and Technology, Vol. 7, No. 2, pp. 144–152.
N. Mache, R. Hubner, G. Mamier, and M. Vogt (1993). SNNS, Report No. 3/93, Institute for Parallel and distributed High Performance Systems, Germany.
W. Van Melle (1980). A Domain-Independent System That Aids in Constructing Knowledge-Based Consultation Programs, Ph.D. Dissertation, Report STAN-CS-80-820, Computer Science Department, Stanford University, CA.
C. Zhang (1992). Cooperation under Uncertainty in Distributed Expert Systems, Artificial Intelligence, 56, pp. 21–69.
M. Zhang and C. Zhang (1994). A Comprehensive Strategy for Conflict Resolution in Distributed Expert Systems, Australian Journal of Intelligent Information Processing Systems, Vol. 1, No. 2, pp. 21–28.
M. Zhang and C. Zhang (1994). Synthesis of Solutions in Distributed Expert Systems. In Artificial Intelligence — Sowing the Seeds for the Future, edited by Chengqi Zhang, John Debenham and Dickson Lukose, World Scientific Publishers, Singapore, pp. 362–369.
M. Zhang and C. Zhang (1995). A Dynamic Neural Network Mechanism for Solving Belief Conflict in Distributed Expert Systems. In Proceedings of Sixth Australian Conference on Neural Networks, Sydney, Australia, pp. 105–108.
M. Zhang and C. Zhang (1995). The Synthesis Strategies for Non-conflict Cases in Distributed Expert Systems. AI'95, World Scientific Publishers, Singapore, pp. 195–202.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, M., Zhang, C. (1996). Neural network strategies for solving synthesis problems in non-conflict cases in distributed expert systems. In: Zhang, C., Lukose, D. (eds) Distributed Artificial Intelligence Architecture and Modelling. DAI 1995. Lecture Notes in Computer Science, vol 1087. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61314-5_29
Download citation
DOI: https://doi.org/10.1007/3-540-61314-5_29
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61314-5
Online ISBN: 978-3-540-68456-5
eBook Packages: Springer Book Archive