Structural learning with forgetting

Neural Networks

Volumn 9, Issue 3, 1996, Pages 509-521

  Ishikawa, Masumi ^a  

^a KYUSHU INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

AIC; Classification; Forgetting; Recurrent network; Regularity discovery; Rule extraction; Structural learning; Time series prediction

Indexed keywords

BACKPROPAGATION; BOOLEAN FUNCTIONS; COMPUTATIONAL COMPLEXITY; LEARNING ALGORITHMS; NEURAL NETWORKS;

CLASSIFICATION; RECURRENT NETWORK; REGULARITY DISCOVERY; RULE EXTRACTION; STRUCTURAL LEARNING WITH FORGETTING; TIME SERIES PREDICTION;

LEARNING SYSTEMS;

ARTIFICIAL NEURAL NETWORK; LEARNING; PRIORITY JOURNAL; REVIEW;

EID: 0030130724     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(96)83696-3     Document Type: Article

References (28)

1. Akaike, H. (1974). A new look at the statistical model identification. IEEE Trans. on Automatic Control, AC-19(6), 716-723.
2. Buntine, W., & Weigend, A. S. (1991). Bayesian back-propagation. Complex Systems, 5, 603-643.
3. Fahlman, S. E., & Lebiere, C. (1990). The cascade-correlation learning architecture. In D. S. Touretzky (Ed.), Advances in neural information processing systems (Vol. 2, pp. 642-649). San Mateo, CA: Morgan Kaufmann.
4. Fisher, R. A. (1936). The use of multiple measurements in taxonomic problem. Annals of Eugenics, 7(2), 179-188.
5. Fogel, D. B. (1991). An information criterion for optimal neural network selection. IEEE Trans. on Neural Networks, 2(5), 490-497.
6. Fu, L. M. (1993), Knowledge-based connectionism for revising domain theories. IEEE Trans. on SMC, 23(1), 173-182.
7. Ishikawa, M. (1989). A structural learning algorithm with forgetting of link weights. IJCNN, II-626, Washington DC, also (1990). Technical Report TR-90-7, Electrotechnical Laboratory, Japan.
8. Ishikawa, M. (1994a). Structural learning and its applications to rule extraction. Proceedings of ICNN'94, (pp. 354-359). Orlando, FL.
9. Ishikawa, M. (1994b). Structural learning in neural networks. Proceedings of 3rd International Conference on Fuzzy Logic, Neural Nets and Soft Computing (IIZUKA'94). Plenary Talk (pp. 37-44). Iizuka, Japan.
10. Ishikawa, M. (1995). Learning of modular structured networks. Artificial Intelligence, 75, 51-62.
11. Ishikawa, M., & Uchida, H. (1992). A structural learning of neural networks based on an entropy criterion. IJCNN'92, II375-380, Beijing.
12. Ishikawa, M., Matsuda, T., & Yoshino, K. (In press). A general structural learning with forgetting for recurrent networks and its applications. Progress in Neural Networks.
13. Kowalczyk, A., Ferrá, H. L., & Gardiner, K. (1991). Discovering production rules with higher order neural networks: a case study. Proceedings of Machine Learning, 158-162.
14. Kreider, J., & Haberl, J. (1993). The great energy prediction shootout, concept and summary of the first building data analysis and prediction competition.
15. Kurita, T. (1990). A method to determine the number of hidden units of three layered neural networks by information criteria. Trans. Inst. Electronics, Information and Communication Engineers, J73-D-II(11), 1872-1878 (in Japanese).
16. Le Cun, Y., Denker, J. S., & Solla, S. A. (1990). Optimal brain damage. In D. S. Touretzky (Ed.), Advances in neural information processing systems (Vol. 2, pp. 598-605). San Mato, CA: Morgan Kaufmann.
17. MacKay, D. J. C. (In press). Probable networks and plausible predictions - a review of practical Bayesian methods for supervised neural networks. Network.
18. Mahoney, J. J., & Mooney, R. J. (1993). Combining connectionist and symbolic learning to refine certainty-factor rule bases. Connection Science, 5(3, 4), 339-364.
19. Moody, J. E. (1992). The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems. In Advances in Neural Information Processing Systems (Vol. 4, pp. 847-854). San Mateo, CA: Morgan Kaufmann.
20. Mozer, M. C., & Smolensky, P. (1989). Using relevance to reduce network size automatically. Connection Science, 1(1), 3-16.
21. Murata, N., Yoshizawa, S., & Amari, S. (1994). Network information criterion - Determining the number of hidden units for an artificial neural network model. IEEE Trans. on Neural Networks, 5(6), 865-872.
22. Murphy, P. M., & Aha, D. W. (1992). UCI Repository of machine learning databases. Department of Information and Computer Science, University of California, Irvine, CA.
23. Plaut, D. C., Nowlan, S. J., & Hinton, G. E. (1986). Experiments on learning by back propagation. Technical Report CMU-CS-86-126, Carnegie-Mellon University.
24. Reed, R. (1993). Pruning algorithms - a survey. IEEE Trans. on Neural Networks, 4(5), 740-747.
25. Rumelhart, D. E. (1988). Parallel distributed processing. IEEE International Conference on Neural Networks, Plenary session, San Diego, CA.
26. Towell, G. G., & Shavlik, J. W. (1993). Extracting refined rules from knowledge-based neural networks. Machine Learning, 13, 71-101.
27. Williams, R. J., & Zipser, D. (1995). Gradient-based learning algorithm for recurrent networks. In Y. Chauvin & D. E. Rumelhart (Eds.), Back-propagation: theory, architectures and applications. Hillsdale, NJ: Erlbaum.
28. Yasui, S. (1992). A new method to remove redundant connections in backpropagation neural networks: Introduction of "parametric lateral inhibition fields." IJCNN'92, pp. II360-367, Beijing.