Neural Network Pruning with Tukey-Kramer Multiple Comparison Procedure

Neural Computation

Volumn 14, Issue 5, 2002, Pages 1149-1168

  Duckro, Donald E ^a   Quinn, Dennis W ^a   Gardner III, Samuel J ^a  

^a AIR FORCE INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER SIMULATION;

ALGORITHMS; COMPUTER SIMULATION; NEURAL NETWORKS (COMPUTER);

EID: 0036584581     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976602753633420     Document Type: Article

References (18)

1. Bishop, C. M. (1995) Neural networks for pattern recognition. New York: Oxford University Press.
2. Brown, L. D. (1984) A note on the Tukey-Kramer procedure for pairwise comparisons of correlated means. In T. J. Santner & A. C. Tamhane (Eds.), Design of experiments: Ranking and selection (pp. 1-6). New York: Marcel Dekker.
3. Efron, B. (1982) The jackknife, the bootstrap and other resampling plans. Philadelphia: Society for Industrial and Applied Mathematics.
4. Gorodkin, J., Hansen, L. K., Lautrup, B., & Solla, S. A. (1997). Universal distribution of saliencies for pruning in layered neural networks. International Journal of Neural Systems, 8, 489-498.
5. Hadzikadic, M., & Bohren, B. F. (1997) Learning to predict: INC2.5. IEEE Transactions on Knowledge and Data Engineering, 9(1), 168-173.
6. Hassibi, B., & Stork, D. G. (1993). Second order derivatives for network pruning: Optimal Brain Surgeon. In C. L. Giles, S. J. Hanson, & J. D. Cowan (Eds.), Advances in neural information processing systems, 5 (pp. 164-171). San Mateo CA: Morgan Kaufmann.
7. Hassibi, B., Stork, D. G., & Wolff, G. (1994). Optimal Brain Surgeon: Extensions and performance comparisons. In J. D. Cowan, G. Tesauro, & J. Alspector (Eds.), Advances in neural information processing systems, 6 (pp. 263-270). San Mateo CA: Morgan Kaufmann.
8. Kramer, C. Y. (1957). Extension of multiple range tests to group correlated adjusted means. Biometrics, 13, 13-18.
9. Le Cun, Y., Denker, J. S., & Solla, S. A. (1990). Optimal Brain Damage. In D. Touretzky (Ed.), Advances in neural information processing systems, 2 (pp. 598-605). San Mateo CA: Morgan Kaufmann.
10. Neter, J., Kutner, M. H., Nachtsheim, C. J., & Wasserman, W. (1996). Applied linear statistical models. Chicago: Irwin.
11. Setiono, R. (1997). A penalty function approach for pruning feedforward neural networks. Neural Computation, 9, 185-204.
12. Thrun, S. B., Wnek, J., Michalski, R. S., Mitchell, T., & Cheng, J. (1991). The Monk's problems - a performance comparison of different algorithms. (Tech. Rep. No. CMU-CS-91-197). Pittsburgh: Carnegie Mellon University, Computer Science Department.
13. Tukey, J. W. (1991). The philosophy of multiple comparisons. Statistical Science, 6(1), 100-116.
14. van de Laar, P., & Heskes, T. (1999). Pruning using parameter and neuronal metrics. Neural Computation, 11, 977-993.
15. Wald, A. (1943). Tests of statistical hypotheses concerning several parameters when the number of observations is large. Transactions of the American Mathematical Society, 54, 426-482.
16. White, H. (1989). Learning in artificial neural networks: A statistical perspective. Neural Computation, 1, 425-464.
17. Widrow, B., & Hoff, M. E. (1960). Adaptive switching circuits. IRE WESCON Convention Record, 4, 94-104.
18. Young S., & Downs, T. (1998). "CARVE - a constructive algorithm for real-valued examples." IEEE Transactions on Neural Networks, 9(6), 1180-1190.