Using input parameter influences to support the decisions of feedforward neural networks

Neurocomputing

Volumn 24, Issue 1-3, 1999, Pages 191-206

  Howes, Peter ^a   Crook, Nigel ^a  

^a OXFORD BROOKES UNIVERSITY   (United Kingdom)

Author keywords

Explanation; Neural network; Parameter influence; Rule extraction; Sensitivity analysis

Indexed keywords

ALGORITHMS; DECISION THEORY; SENSITIVITY ANALYSIS;

RULE EXTRACTION;

FEEDFORWARD NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER LANGUAGE; DECISION MAKING; HEALTH CARE QUALITY; MATHEMATICAL COMPUTING; PRIORITY JOURNAL; TECHNOLOGY;

EID: 0033082449     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(98)00102-7     Document Type: Article

References (34)

1. Andrews R., Diederich J., Tickle A.B. Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems. 8:1995;373-389.
2. Belue L.M., Bauer K.W. Determining input features for multilayer perceptrons. Neurocomputing. 7:1995;111-121.
3. Brill F.Z., Brown D.E., Martin W.N. Fast genetic selection of features for neural network classifiers. IEEE Trans. Neural Networks. 3:1992;324-328.
4. Cawsey A. Explanation and Interaction. 1992;MIT Press, Cambridge, MA.
5. E. Collins, S. Ghosh, C.L. Schofield, An application of a multiple neural network learning system to emulation of mortgage underwriting judgements, IEEE Int. Conf. on Neural Networks, San Diego, CA, Ud. II, 1988, pp. 459-466.
6. M.W. Craven, J.W. Shavlik, Learning symbolic rules using artificial neural networks, Proc. 10th Int. Conf. on Machine Learning, Morgan Kaufmann, Amherst, MA, 1993, pp. 73-80.
7. M.W. Craven, J.W. Shavlik, Using sampling and queries to extract rules from trained neural networks, Machine Learning: Proc. 11th Int. Conf., Morgan Kaufmann, San Francisco, CA, 1994, pp. 37-45.
8. Craven M.W., Shavlik J.W. Extracting Tree-Structured Representations of Trained Networks, Advances, Neural Information Processing Systems 8. 1996;MIT Press, Cambridge, MA.
9. N.T. Crook, The theory of explanation applied to medical expert systems, Ph.D. Thesis, School of Computing and Mathematical Sciences, Oxford Brookes University, 1992.
10. Diederich J. Explanation and artificial neural networks. Int. J. Man-Mach. Stud. 37:1992;335-355.
11. R.C. Eberhart, The role of genetic algorithms in neural network query-based learning and explanation facilities, in: L.D. Whitley, J.D. Schaffer (Eds.), COGANN-92: Int. Workshop on Combinations of Genetic Algorithms and Neural Networks, IEEE Computer Society Press, Loa Alamitos, CA, 1992, 169-183.
12. Eberhart R.C. Using evolutionary computation tools in explanation facilities. Int. J. Expert Systems. 8:1995;277-285.
13. A.P. Engelbrecht, I. Cloete, J.M. Zurada, Determining the Significance of Input Parameters Using Sensitivity Analysis, Lecture Notes Computer Science, vol. 930, 1995, pp. 382-388.
14. LiMin Fu, Rule generation from neural networks, IEEE Trans. Systems Man Cybernet. 24 (1994) 1114-1124.
15. Gallant S.I. Neural Network Learning and Expert Systems. 1993;MIT Press, Cambridge, MA.
16. G.D. Garson, Interpreting neural-network connection weights, AI Expert (1991) 47-51.
17. Gilbert N. Explanation and dialogue, Knowledge Eng. Rev. 4:1989;235-247.
18. Horimoto Y., Durance T., Nakai S., Lukow O.M. Neural networks versus principal component regression for prediction of wheat flour loaf volume in baking tests. J. Food Sci. 60:1995;429-433.
19. P.J. Howes, N.T. Crook, Rule extraction from neural networks, Proc. Rule Extraction from Trained Artificial Neural Networks Workshop, University of Sussex, Brighton, April 1996, pp. 60-67.
20. Jang G.S., Lai F.P., Jiang B.W., Paring T.M., Chien L.H. Intelligent stock trading system with price trend prediction and reversal recognition using dual-module neural networks. App. Intell. 3:1993;225-248.
21. Kimoto T., Yoda M. Buying and selling timing prediction system for stocks based on modular neural networks. Fujitsu Sci. Tech. J. 29:1993;257-264.
22. Ma Z., Harrison R.F., Kennedy R.L. A heuristic for general rule extraction from a multilayer perceptron. Hallam J.et al. Hybrid Problems, Hybrid Solutions. 1995;IOS Press, Amsterdam.
23. J.D. Moore, A reactive approach to explanation in expert and advice-giving systems, Ph.D. Thesis, Department of Computer Science, University of California, Los Angeles, CA, USA, 1989.
24. J.D. Moore, W.R. Swartout, A Reactive Approach to Explanation, IJCAI-89, Morgan Kaufman, Los Altos, CA, 1989, 1504-1510.
25. Omlin C.W., Giles C.L. Extraction of rules from discrete-time recurrent neural networks. Neural Networks. 9:1996;41-52.
26. Press W.H., Teukolsky S.A., Vetterling W.T., Flannery B.P. Numerical Recipes in FORTRAN-The Art of Scientific Computing. 1992;Cambridge Univerity Press, Cambridge.
27. Refenes A.N., Zapranis A., Francis G. Stock performance modeling using neural networks: a comparative study with regression models. Neural Networks. 7:1994;375-388.
28. K. Saito, R. Nakano, Medical diagnostic expert system based on PDP model, Proc. IEEE Int. Conf. on Neural Networks, San Diego, CA, USA, vol. 1, 1988, pp. 255-262.
29. S.B. Thrun, Extracting provably correct rules from artificial neural networks, Technical Report IAI-TR-93-5, Institut für Informatik III, Universität Bonn, 1993.
30. Thrun S.B. Extracting rules from artificial neural networks with distributed representations. Tesauro G., Touretzky D., Leen T. Advances in Neural Information Processing Systems. 7:1995;MIT Press, Cambridge, MA.
31. Towell G.G., Shavlik J.W. Extracting refined rules from knowledge-based neural networks. Mach. Learning. 13:1993;71-101.
32. U. Visser, A. Tickle, R. Hayward, R. Andrews, Rule-extraction from trained neural networks: different techniques for the determination of herbicides for the plant protection advisory system PRO_PLANT, Proc. Rule Extraction from Trained Artificial Neural Networks Workshop, University of Sussex, Brighton, April 1996, pp. 122-130.
33. Yoon Y., Guimaraes T., Swales G. Integrating artificial neural networks with rule-based expert systems. Decision Support Systems. 11:1994;497-507.
34. J.M. Zurada, A. Malinowski, I. Cloete, Sensitivity analysis for minimisation of input data dimension for feedforward neural networks, IEEE Int. Symp. on Circuits and Systems, London, 30 May- 3 June 1994.