Abstract
In this paper a new knowledge incorporation and rule extraction method in neural networks is presented. The rule form of an if-then type can be inserted into a neural network (NN) as knowledge of a problem. NN is then trained by using a set of training samples. In this case the structure learning algorithm with forgetting is used to generate a small-sized NN system. After the NN training, rules are extracted from it.
The results of computer simulations show that this approach can generate obvious network architectures and as a result simple rules compared with conventional rule extraction methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
A.B. Tickle et al.: “The Truth Will Come to Light: Directions and Challenges in Extracting the Knowledge Embedded within Trained Artificial Neural Networks”, IEEE Trans. NN, Vol. 9, No. 6, pp. 1057–1067 (1998)
M. Fukumi and N. Akamatsu: “A Method to Design a Neural Pattern Recognition System by Using a Genetic Algorithm with Partial Fitness and a Deterministic Mutation”, Proc. of IEEE Int. Conf. on SMC, Vol. 3, pp. 1989–1993 (1996)
M. Fukumi and N. Akamatsu: “Rule Extraction from Neural Network Trained Using Evolutionary Algorithms with Deterministic Mutation”, Proc. of IJCNN, pp. 686–689 (1998)
M. Fukumi and N. Akamatsu: “A New Rule Extraction Method from Neural Networks”, Proc. of IJCNN, # 713(1999)
M. Ishikawa: “Structural Learning with Forgetting”, Neural Networks, Vol. 9, No. 3, pp. 509–521 (1996)
H. Ueda and M. Ishikawa:“Rule Extraction from Data with Continuous Valued Inputs and Discrete Valued Outputs Using Neural Networks”, Technical Report IEICE Japan, NC96-121, pp. 63–70 (1997), in Japanese
L. Fu: “Rule Generation from Neural Networks”, IEEE Trans. SMC, Vol. 24, No. 8, pp. 1114–1124 (1994)
C. Sano: Learning and Evolution of Intelligent Artificial Life, Morikita-shuppan (1996), in Japanese
A-H. Tan: “Cascade ARTMAP: Integrating Neural Computation and Symbolic Knowledge Processing”, IEEE Trans. on Neural Networks, Vol. 8, No. 2, pp. 237–250 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fukumi, M., Mitsukura, Y., Akamatsu, N. (2001). Knowledge Incorporation and Rule Extraction in Neural Networks. In: Dorffner, G., Bischof, H., Hornik, K. (eds) Artificial Neural Networks — ICANN 2001. ICANN 2001. Lecture Notes in Computer Science, vol 2130. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44668-0_174
Download citation
DOI: https://doi.org/10.1007/3-540-44668-0_174
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42486-4
Online ISBN: 978-3-540-44668-2
eBook Packages: Springer Book Archive