A methodology for simplification and interpretation of backpropagation-based neural network models

Expert Systems with Applications

Volumn 10, Issue 1, 1996, Pages 37-54

  Glorfeld, Louis W ^a  

^a UNIVERSITY OF ARKANSAS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; ARTIFICIAL INTELLIGENCE; BACKPROPAGATION; COMPUTER SIMULATION; DECISION MAKING; EXPERT SYSTEMS; HUMAN COMPUTER INTERACTION; INFERENCE ENGINES; KNOWLEDGE ACQUISITION; LEARNING SYSTEMS; OPACITY;

EXPERT SYSTEM DECISION SUPPORT TOOLS; INFERENCE PROCESS;

NEURAL NETWORKS;

EID: 0029779184     PISSN: 09574174     EISSN: None     Source Type: Journal    
DOI: 10.1016/0957-4174(95)00032-1     Document Type: Article

References (38)

1. Atlas, L., Cole, R., Connor, J., El-Sharkawi, M., Marks II, R. J., Muthusany, Y., & Barnard, E. (1990). Performance comparisons between backpropagation networks and classification trees on three real world applications. In Touretzky, D. S. (Ed), Advances in Neural Information Processing Systems 2 pp. 441-449. San Mateo, CA: Morgan Kaufmann Publishers.
2. Barr, A. & Feigenbaum, E. A. (1982). The Handbook of Artificial Intelligence (Vol II). London: Pitman Books, Ltd.
3. Bratko, I. & Michie, D. (1987). Some comments on rule induction. Knowledge Engineering Review, 2, 65-67.
4. Breiman, L., Friedman, J., Olshen, R., & Stone, C. (1984). Classification and Regression Trees. Reading, MA: Wadsworth Publishing Co.
5. Carpenter, W. C. & Hoffman, M. E. (1995). Training backprop neural networks. AI Expert, 10(3), 30-33.
6. Caudill, M. (1988). Neural networks primer part III. AI Expert, 5(6), 53-59.
7. Caudill, M. (1991). Neural network training tips and techniques. AI Expert, 6(1), 56-61.
8. Chatterjee, S. & Price, B. J. (1992). Regression Analysis by Example. New York: John Wiley & Sons.
9. Dawes, R. M. (1979). The robust beauty of improper linear models in decision making. American Psychologist, 34(7), 571-82.
10. Deng, Pi-Sheng. (1993). Automatic knowledge acquisition and refinement for decision support: A connectionist inductive inference model. Decision Sciences, 24(2), 371-393.
11. Denton, J. W., Hung, M. S., & Osyk, B. A. (1990). A neural network approach to the classification problem. Expert Systems with Applications, 1, 417-424.
12. Efron, Bradely. (1982). The Jackknife, the Bootstrap and other Resampling Plans. Philadelphia, PA: Society for Applied Mathematics.
13. Efron, Bradely & Tibshirani, R. J. (1993). An introduction to the bootstrap. New York: Chapman & Hall, 237-257.
14. Fisher, R. A. (1936). The use of multiple measurements in taxonomy problems. Annuals of Eugenics, 7, 179-188.
15. Gallant, Stephen L. (1993). Neural Network Learning and Expert Systems. Cambridghe MA: MIT Press.
16. Garson, G. David. (1991). Interpreting neural-network connection weights. AI Expert, 6(4), 47-51.
17. Goodman, R. M., Hggins, C. M. & Miller, J. M. (1992). Rule-based neural networks for classification and probability estimation. Neural Computation, 4, 781-804.
18. Hanson, J. V., McDonald, James B. & Stice, J. D. (1992). Artificial intelligence and generalized qualitative-response models: An empirical test on two audit decision-making domains. Decision Sciences, 23(3), 704-723.
19. Hart, A. (1986). The role of induction in knowledge acquisition. Expert Systems, 2, 24-28.
20. Hecht-Nielsen, R. (1989). Neurocomputing. Reading MA: Addison-Wesley.
21. Hocking, R. R. (1976). The analysis and selection of variables in linear regression. Biometrics, 32, 1-49
22. James, M. (1985). Classification algorithms. New York: John Wiley & Sons.
23. Kilmasauskas, C. C. (1988). NeuralWorks: An introduction to neural computing. Sewickley, PA: NeuralWare, Inc.
24. Knight, K. (1990). Connectionist ideas and algorithms. Communications of the ACM, 33(11), 59-74.
25. Krzanowski, W. J. (1988). Principles of Multivariate Analysis: A Users Perspective. Oxford: Claredon Press.
26. LeCun, Y., Denker, J. S. & Solla, S. A. (1990). Optimal brain damage. -In Touretzky, D. S. (Ed), Advances in Neural Information Processing Systems 2, pp. 598-605. San Mateo, CA: Morgan Kaufmann Publishers, 1990.
27. Meehl, P. E. (1954). Clinical Versus Statistical Prediction: A Theoretical Analysis and Review of the Evidence. Minneapolis, MN: U. of Minnesota Press.
28. Nath, R. & Rajagopalan, B. (1994). Detemiining the salency of input variables in neural network classifiers. 1994 Proceedings of the Decision Sciences Institute, pp. 1294-1296. Honolulu, Hawaii.
29. Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning internal representations by error propagation. In Rumelhart, D. E. & McClelland, J. L. (Eds), Parallel Distributed Processing: Volume I, pp. 318-362. Cambridge, MA: The MIT Press.
30. Salchenberger, L. M., Cinar, E. M. & Lash, N. A. (1992). Neural networks: A new tool for predicting thrift failures. Decision Sciences, 23(4), 899-916.
31. Shawlik, J. W., Mooney, R. J. & Towell, G. G. (1991). Symbolic and Neural Learning Algorithms: An experimental comparison. Machine Learning, 6, 111-143.
32. Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society B, 36, 111-48.
33. Tam, K. Y. & Kiang, M. Y. (1992). Managerial applications of neural networks: The case of bank failure predictions. Management Science, 38(7), 926-947.
34. Urban Hjorth, J. S. (1994). Computer intensive statistical methods: Validation, model selection and bootstrap. New York: Chapman & Hall.
35. Wasserman, P. D. (1989). Neural computing: Theory and practice. New York: Van Nostrand.
36. White, H. (1989). Some asymptotic results for learning in single hidden-layer feedforward network models. Journal of the American Statistical Association, 84(408), 1003-1013.
37. Whitley, L., Dominic, S. & Das, R. (1991). Genetic reinforcement learning with multilayer neural networks. The Proceedings of the Fourth International Conference on Genetic Algorithms, pp. 101-108. San Mateo, CA: Morgan Kaufmann.
38. Yoon, Y. & Peterson. L. (1992). Artificial neural networks: an emerging new technique. Data Base, 23(1), 55-57.