Discriminant component pruning: Regularization and interpretation of multilayered backpropagation networks

Neural Computation

Volumn 11, Issue 3, 1999, Pages 783-802

  Koene, Randal A ^a   Takane, Yoshio ^a  

^a MCGILL UNIVERSITY   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; APTITUDE; ARTIFICIAL NEURAL NETWORK; DISCRIMINANT ANALYSIS; REGRESSION ANALYSIS; REVIEW; STATISTICAL ANALYSIS;

ALGORITHMS; APTITUDE; DATA INTERPRETATION, STATISTICAL; DISCRIMINANT ANALYSIS; NEURAL NETWORKS (COMPUTER); REGRESSION ANALYSIS;

EID: 0033114133     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976699300016665     Document Type: Article

References (19)

1. Anderson, T. (1951). Estimating linear restrictions on regression coefficients for multivariate normal distributions. Annals of Mathematical Statistics, 22, 327-351.
2. Fisher, R. (1936). The use of multiple measurements in axonomic problems. Annals of Eugenics, 7, 179-188.
3. Flury, B. (1995). Developments in principal component analysis. In W. J. Krzanowski (Ed.), Recent advances in descriptive multivariate analysis, pp. 14-33. Oxford: Oxford Science Publications.
4. Hanson, S., & Pratt, L. (1989). Comparing biases for minimal network construction with back-propagation. In D. Touretzky (Ed.), Advances in neural information processing, 1 (pp. 177-185). San Mateo, CA: Morgan Kauffman.
5. Hassibi, B., Stork, D., & Wolff, G. (1992) Optimal brain surgeon and general network pruning (Tech. Rep. No. 9235). Menlo Park, CA: RICOH California Research Center.
6. Jolliffe, I. (1986). Principal component analysis. New York: Springer-Verlag.
7. Koene, R. Extracting knowledge in terms of rules from trained neural networks. Unpublished master's thesis, Department of Electrical Engineering, Delft University of Technology, Delft, Netherlands.
8. Kurita, T. (1989). A method to determine the number of hidden units of three layered neural networks by information criteria. Transactions of the Institute of Electronics, Information and Communication Engineers, J73-D-II, No. 11 (pp. 1872-1878). (in Japanese)
9. Le Cun, Y., Denker, J., & Solla, S. (1990). Optimal Brain Damage. In D. Touretzky (Ed.), Advances in neural information processing systems, 2 (pp. 598-605). San Mateo, CA: Morgan Kauffman.
10. Levin, A., Leen, T., & Moody, J. (1994). Fast pruning using principal components. In J. D. Cowan, G. Tessauro, & J. Alspector (Eds.), Advances in neural information processing systems, 6 (pp. 35-42). San Mateo, CA: Morgan Kauffman.
11. LiMin, F. (1994). Rule generation from neural networks. IEEE Transactions on Systems, Man and Cybernetics, 24, 1114-1124.
12. Maclin, R., & Shavlik, J. (1991). Refining domain theories expressed as finite-state automata. Machine Learning: Proceedings of the Eighth International Workshop (pp. 524-528).
13. Mozer, M., & Smolensky, P. (1989). Skeletonization: A technique for trimming the fat from a network via relevance assessment. In D. Touretzky (Ed.), Advances in neural information processing systems, 1 (pp. 107-115). San Mateo, CA: Morgan Kauffman.
14. Mulaik, S. A. (1972). The foundations of factor analysis. New York: McGraw-Hill.
15. Reed, R. (1993). Pruning algorithms - a survey. IEEE Transactions on Neural Networks, 4-5, 740-747.
16. Rumelhart, D., Hinton, G., & Williams, R. (1986). Learning internal representations by error propagation. In D. E. Rumelhart & J. L. McClelland (Eds.), Parallel distributed processing: Explorations in the microstructure of cognition, 1 (pp. 318-362). Cambridge, MA: MIT Press.
17. Takane, Y., & Shibayama, T. (1991). Principal component analysis with external information on both subjects and variables. Psychometrika, 56, 97-120.
18. Towell, G., Shavlik, J., & Noordewier, M. (1990). Refinement of approximate domain theories by knowledge-based neural networks. AAAI90, 861-866.
19. Toyoda, H. (1996). Nonlinear multivariate analysis by neural network models. Tokyo: Asokura Shoten. (in Japanese)