Inversion of feedforward neural networks: Algorithms and applications

Proceedings of the IEEE

Volumn 87, Issue 9, 1999, Pages 1536-1549

  Jensen, Craig A ^a   Reed, Russell D ^a   Marks II, Robert J ^a   El Sharkawi, Mohamed A ^b   Jung, Jae Byung ^a   Miyamoto, Robert T ^a   Anderson, Gregory M ^a   Eggen, Christian J ^a  

^a University of Washington   (United States)

^b UNIVERSITY OF WASHINGTON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; CONSTRAINT THEORY; LEARNING SYSTEMS;

QUERY-BASED LEARNING;

FEEDFORWARD NEURAL NETWORKS;

EID: 0033359396     PISSN: 00189219     EISSN: None     Source Type: Journal    
DOI: 10.1109/5.784232     Document Type: Article

References (39)

1. J. N. Hwang, J. J. Choi, S. Oh, and R. J. Marks, II, "Query based learning applied to partially trained multilayer perceptrons," IEEE Trans. Neural Nef'orks, vol. 2, pp. 131-136, 1991.
2. R. J. Williams, "Inverting a connectionist network mapping by backpropagation of error," in Proc. 8th Anna. Conf. Cognitive Science Society. Hillsdale, NJ: Lawrence Erlbaum, 1986, pp. 859-865.
3. A. Linden and J. Kindermann, "Inversion of multilayer nets," in Proc. Int. Joint Conf. Neural Netvsorks, vol. II, Washington, DC, 1989, pp. 425-430.
4. J. N. Hwang, J. J. Choi, S. Oh, and R. J. Marks II, "Classification boundaries and gradients of trained multilayer perceptrons," in Proc. IEEE Int. Symp. Circuits and Systems, 1990, pp. 3256-3259.
5. R. C. Eberhart and R. W. Dobbins, "Designing neural network explanation facilities using genetic algorithms," in Proc. Int. Joint Conf. Neural Netn-orks, vol. II, Singapore, 1991, pp. 1758-1763.
6. R. D. Reed and R. J. Marks, II, "An evolutionary algorithm for function inversion and boundary marking," in Proc. IEEE Int. Conf. Evolutionary Computation (ICEC'95), Perth, Western Australia, 1995, pp. 794-797.
7. _, Neural Smithing: Supervised Learning in Feedfonvard Artificial Neural Nenvorks. Cambridge, MA: MIT Press, 1999.
8. D. B. Fogel, Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. Piscataway, NJ: IEEE Press, 1995.
9. Z. Michalewicz, Genetic Algorithms + Data Structures = Evolution Programs, 3rd ed. Berlin, Germany: Springer-Verlag, 1996.
10. D. B. Fogel, Ed., Evolutionary Computation: The Fossil Record. Piscataway, NJ: IEEE Press, 1998.
11. D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning. Reading, MA: Addison-Wesley, 1989.
12. J. Linderman and A. Linden, "Inversion of neural networks by gradient descent," Parallel Compitt., pp. 277-286, 1990.
13. R. Reed, R. J. Marks II, and S. Oh, "Similarities of error regularization, sigmoid gain scaling, target smoothing and training with jitter," IEEE Trans. Neural NeMorks, vol. 6, pp. 529-538, May 1995.
14. J. N. Hwang, C. H. Chan, and R. J. Marks II, "Frequency selective surface design based on iterative inversion of neural networks," in Proc. Int. Joint Conf. Neural Netvorks (IJCNN '90), vol. I, San Diego, CA, 1990, pp. 39-44.
15. R. J. Marks II, "Alternating projections onto convex sets," in Deconvolution of Images and Spectra, P. A. Jansson, Ed. San Diego, CA: Academic, 1997, pp. 476-501.
16. D. T. Davis, J. N. Hwang, and J. S. Lee, "Improved network inversion technique for query learning: Application to automated cytology screening," in Proc. Conipnter-Based Medical Systems: 4th Annn. IEEE Symp., Baltimore, MD, 1991, pp. 313-320.
17. D. T. Davis and J. N. Hwang, "Attentional focus training by boundary region data selection," in Proc. Int. Joint Conf. Ne lirai Ne works, (IJCNN'92), Baltimore, MD, June 1992, pp. 676-681.
18. C. A. Jensen, R. D. Reed, M. A. EI-Sharkawi, and R. J. Marks II, "Location of operating points on the dynamic security border using constrained neural network inversion," in Proc. Int. Conf. Intelligent Systems Applications to Power Systems, (ISAP'97), Seoul, Korea, July 1997.
19. M. A. El-Sharkawi and S. S. Huang, "Query-based learning neural network approach to power system dynamic security assessment," in Proc. 1993 Int. Symp. Nonlinear Theory and Its Applications (NOLTA'93), Hawaii, Dec. 1993.
20. _, "Application of query-based learning to power system static security assessment," in Proc. 2nd Int. Forum on Applications of Neural Nenrorks to Power Systems (ANNPS'93), Yokohama, Japan, Apr. 1993, pp. 111-117.
21. EPRI, "Extended transient midterm stability program: Version 3.0," Palo Alto, CA, EPRI TR-102004, vol. 1-6, 1993.
22. IEEE Committee Report, "Transient stability test systems for direct stability methods," IEEE Trans. Power Syst., vol. 7, pp. 37-44, Feb. 1992.
23. J. N. Hwang and C. J. Wang, "Classification of incomplete data with missing elements," in 1994 Int. Symp. Artificial Neural Nehvorks, (ISANN'94), Tainan, Taiwan, Dec. 1994, pp. 471-477.
24. D. A. Hoskins, J. N. Hwang, and J. Vagners, "Iterative inversion of neural networks and its application to adaptive control," IEEE Trans. Neural Nerwrks, vol. 3, pp. 292-301, Mar. 1992.
25. R. D. Reed, R. J. Marks, II, C. A. Jensen, and M. A. ElSharkawi, "A neural network inversion procedure," in Int. Joint Conf. Neural Networks (IJCNN'9S), Anchorage, AK, 1998.
26. P. Martin and J. R. Millan, "Combining reinforcement learning and differential inverse kinematics for collision-free motion of multilink manipulators," in Int. Work-Conf. Artificial and Natural Neural Netn-orks, (IWANN'97), Lanzarote, Spain, June 1997, pp. 1324-1333.
27. L. Behera, M. Gopal, and S. Chaudhury, "On adaptive trajectory tracking of a robot manipulator using inversion of its neural emulator," IEEE Trans. Neural Networks, vol. 7, no. 6, Nov. 1996.
28. K. Yoshitomi, A. Ishimaru, J. N. Hwang, and J. S. Chen, "Surface roughness determination using spectral correlations of scattered intensities and an artificial neural network technique," IEEE Trans. Antennas Propagat., vol. 41, pp. 498-502, Apr. 1993.
29. M. Sase, N. Kinoshita, and Y. Kosugi, "A neural network for fusing the MR information into PET images to improve spatial resolution," in Proc. (ICIP'94), vol. 3, Austin, TX, Nov. 1994, pp. 908-911.
30. M. Ishida and J. Zhan, "Neural model-predictive control of distributed parameter crystal growth process," AICHE J., vol. 41, no. 10, pp. 2333-2336, Nov. 1995.
31. G. C. Vasconcelos, M. C. Fairhurst, and D. L. Bisset, "Enhanced reliability of multilayer perceptron networks through controlled pattern rejection," Electron. Lett., vol. 29, no. 3, pp. 261-263, 1993.
32. A. P. Weijer, C. B. Lucasius, L. Buydens, and G. Kateman, "Using genetic algorithms for an artificial neural network model . inversion," Chemometrics Intell. Lab. Syst.. vol. 20, no. 1, pp. 45-55, Aug. 1993.
33. J. N. Hwang and C. H. Chan, "Iterative constrained inversion of neural networks and its applications," in P roc. 24th Conf. Inform. Sei. Syst., Princeton, NJ, Mar. 1990, pp. 754-759.
34. J. Takeuchi and Y. Kosugi, "Neural network representation of finite element method," Neural Nehvorks, vol. 7, no. 2, pp. 389-395, 1994.
35. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," in Parallel Distributed Processing (POP): Exploration in the Microstructiire of Cognition. Cambridge, MA: MIT Press, 1986, vol. 1.
36. M. I. Jordan and D. E. Rumelhart, "Forward models: Supervised learning with a distal teacher," Cognitive Sei., vol. 16, pp. 307-354, 1992.
37. M. I. Jordan, "Constrained supervised learning," J. Math. Psych., vol. 36,.pp. 396-425, 1992.
38. B. L. Lu, H. Kita, and Y. Nishikawa, "Inversion of feedforward neural networks by a separable programming," in Proc. World Congr. Neural Net\-orks (Portland), vol. 4, 1993, pp. 415-420.
39. _, "A new method for inverting nonlinear multilayer feedforward networks," in Proc. Int. Conf. Industrial Electronics, Control and Instrumentation, Kobe, Japan, 1991, pp. 1349-1354.