Abstract
By comparison with constraint satisfaction networks, this paper presents an essential frame of the logical theory for continuous-state neural networks, and gives the quantitative analyzing method for contradiction. The analysis indicates that the basic reason for the alternation of the logical states of the neurons is the existence of superior contradiction inside the networks. The dynamic process for a neural network to find a solution corresponds to eliminating the superior contradiction.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
U. Montanari, F. Rossi, Constraint relaxation may be perfect, Artificial Intelligence, 48(1991) 2, 143–170.
D. S. Touretzky, G. E. Hinton, A distributed connectionist production system, Cognitive Science, 12(1988)3, 423–466.
H. W. Guesgen, J. Hertzberg, A constraint-based approach to sptiotemporal reasoning, J. Applied Intelligence, 3(1991)1, 71–90.
J. J. Hopfield, Neurons with graded response have collective computational properties like those of two-state neurons, Proc. Natl. Acad. Sci. USA, 81(1984), 3088–3092.
T. J. Sejnowski, P. K. Kienker, G. E. Hinton, Learning symmetry groups with hidden units: beyond the perceptron, Physica, 1988, 22D: 260–275.
S. Grossberg, E. Mingolla, D. Todorovic, A neural network architecture for preattentive vision, IEEE Trans. on BME, BME-36(1989)1, 65–84.
Author information
Authors and Affiliations
Additional information
Supported by the National Natural Science Foundation of China and the National Hightech Project of China (863).
About this article
Cite this article
Baolong, G., Lei, G. Logical analysis for neural networks. J. of Electron.(China) 14, 117–124 (1997). https://doi.org/10.1007/s11767-997-1003-7
Issue Date:
DOI: https://doi.org/10.1007/s11767-997-1003-7