Abstract
This paper deals with two complementary problems: the problem of extracting knowledge from neural networks and the problem of inserting knowledge into neural networks. Our approach to the extraction of knowledge is essentially constraints-based. Local constraints are imposed on the neural network's weights and activities to make neural networkunits work as logical operators. We have modified two well-known learning algorithms, namely the simulated annealing and the backpropagation, with respect to imposed constraints. In the case of the non-empty domain theory, the knowledge insertion technique is used to impose global constraints to determine the neural network's topology and initialization according to a priori knowledge about the problem under study. The knowledge to be inserted can be expressed as a set of propositional rules. We report simulation results obtained by running our algorithms to extract boolean formulae.
This work is supported by a grant from the DRET
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Bochereau, L., Bourgine, P.: Extraction of semantic features from a multilayer neural network, Proceedings of the IJCNN90, Washington DC.
Masuoka, R., Watanabe, N., Kawamura, A.: Neuro-fuzzy system — fuzzy inference using a structured neural network. In Proc. of the International Conference on Fuzzy Logic and Neural Networks, 173–177, 1990.
Sethi, I.K.: Entropy nets: From decision trees to neural networks. Proc. of the IEEE, vol.78, No.10, 1990.
Towell,G.G., Shavlik, J.W.: The extraction of refined rules from knowledge-based neural networks. Submitted to Machine Learning (8/91).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kane, R., Tchoumatchenko, I., Milgram, M. (1993). Extraction of knowledge from data using constrained neural networks. In: Brazdil, P.B. (eds) Machine Learning: ECML-93. ECML 1993. Lecture Notes in Computer Science, vol 667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56602-3_161
Download citation
DOI: https://doi.org/10.1007/3-540-56602-3_161
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56602-1
Online ISBN: 978-3-540-47597-2
eBook Packages: Springer Book Archive