Visualizing the function computed by a feedforward neural network

Neural Computation

Volumn 12, Issue 6, 2000, Pages 1337-1353

  Plate, Tony A ^a   Bert, Joel ^b   Grace, John ^b   Band, Pierre ^c  

^a BiosGroup Inc   (United States)

^b UNIVERSITY OF BRITISH COLUMBIA   (Canada)

^c HEALTH CANADA   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER GRAPHICS; DRINKING BEHAVIOR; FEEDBACK SYSTEM; HUMAN; LUNG TUMOR; REGRESSION ANALYSIS; RISK ASSESSMENT; SMOKING; SQUAMOUS CELL CARCINOMA; STATISTICAL MODEL;

ALCOHOL DRINKING; CARCINOMA, SQUAMOUS CELL; COMPUTER GRAPHICS; FEEDBACK; HUMANS; LINEAR MODELS; LUNG NEOPLASMS; NEURAL NETWORKS (COMPUTER); REGRESSION ANALYSIS; RISK ASSESSMENT; SMOKING;

EID: 0034201610     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976600300015394     Document Type: Article

References (18)

1. Baxt, W. G. (1992). Analysis of the clinical variables driving decision in an artificial neural network trained to identify the presence of myocardial infarcation. Annals of Emergency Medicine, 21(12), 1439-1444.
2. Baxt, W. G., & H. White (1995). Bootstrapping confidence intervals for clinical input variable effects in a network trained to identify the presence of acute myocardial infarction. Neural Computation, 7, 624-638.
3. Bishop, C. (1995). Neural networks for pattern recognition. New York: Oxford University Press.
4. Blasig, R. (1994). GDS: Gradient descent generation of symbolic classification rules. In J. D. Cowan, G. Tesauro, & J. Alspector (Eds.), Advances in neural information processing systems, 6 (pp. 1093-1100). San Mateo, CA: Morgan Kaufmann.
5. Dodds, S. R. (1995, Dec. 2). Neural networks (letter). Lancet, 346, 1500-1501.
6. Hastie, T. J., & Tibshirani, R. J. (1990). Generalized additive models. London: Chapman and Hall.
7. Hwang, J.-N., Lay, S.-R., Maechler, M., Martin, R. D., & Schimert, J. (1994). Regression modeling in back-propagation and projection pursuit learning. IEEE Transactions on Neural Networks, 5(3), 342-353.
8. MacKay, D. J. C. (1992). The evidence framework applied to classification networks. Neural Computation, 4(5), 698-714.
9. 2, air pollutiion, weather, and medicine intake. Allergy, 48, 334-344.
10. Plate, T. A. (1999). Accuracy versus interpretability in flexible modeling: Implementing a tradeoff using gaussian process models. Behaviourmetrika, 26, 29-50.
11. Plate, T., Bert, J., Grace, J., & Band, P. (1997). A comparison between neural networks and other statistical techniques for modeling the relationship between tobacco and alcohol and cancer. In M. Mozer, M. Jordan, & T. Petsche (Eds.), Advances in neural information processing, 9. Cambridge, MA: MIT Press.
12. Saito, K., & Nakano, R. (1988). Medical diagnostic expert system based on PDP model. In IEEE International Conference on Neural Networks (pp. 255-262). San Diego, CA.
13. Sanger, D. (1989). Contribution analysis: A technique for assigning responsibilities to hidden units in connectionist networks. Connection Science, 1, 115-138.
14. Sharp, D. (1995, Oct. 21). From "black box" to bedside, one day? Lancet, 346, 1050.
15. Shultz, T. R., & Elman, J. L. (1994). Analyzing cross connected networks. In J. D. Cowan, G. Tesauro, & J. Alspector (Eds.), Advances in neural information processing systems, 6 (pp. 1117-1124). San Mateo, CA: Morgan Kaufmann.
16. Shultz, T., Oshima-Takane, Y., & Takane, Y. (1995). Analysis of unstandardized contributions in cross connected networks. In G. Tesauro, D. S., Touretzky, & T. K. Leen (Eds.), Advances in neural information processing systems, 7 (pp. 601-608). Cambridge, MA: MIT Press.
17. Towell, G., & Shavlik, J. (1993). Extracting refined rules from knowledge-based neural networks. Machine Learning, 13(1), 71-101.
18. Wyatt, J. (1995, Nov. 4). Nervous about artificial neural networks? Lancet, 346, 1175-1177.