CATSMLP: Toward a robust and interpretable multilayer perceptron with sigmoid activation functions

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Volumn 36, Issue 6, 2006, Pages 1319-1331

  Chung, Fu Lai ^a   Wang, Shitong ^a,b,c   Deng, Zhaohong ^a,b   Hu, Dewen ^d  

^a HONG KONG POLYTECHNIC UNIVERSITY   (Hong Kong)

^b JIANGNAN UNIVERSITY   (China)

^c INSTITUTE OF SOFTWARE   (China)

^d NATIONAL UNIVERSITY OF DEFENSE TECHNOLOGY   (China)

Author keywords

Cascaded multilayer perceptron (MLP); Fuzzy systems; Robustness analysis; Syllogistic fuzzy inference; Universal approximation

Indexed keywords

APPROXIMATION THEORY; CASCADE CONTROL SYSTEMS; FUZZY INFERENCE; FUZZY NEURAL NETWORKS; FUZZY SYSTEMS; MATHEMATICAL MODELS; ROBUSTNESS (CONTROL SYSTEMS);

APPROXIMATORS; CASCADED MULTILAYER PERCEPTRON (MLP); INTERPRETABILITY; SIGMOID ACTIVATION FUNCTIONS; SYLLOGISTIC FUZZY REASONING; UNIVERSAL APPROXIMATION;

MULTILAYER NEURAL NETWORKS;

EID: 33947110575     PISSN: 10834419     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSMCB.2006.875871     Document Type: Article

References (32)

1. S. T. Wang, Neural-Fuzzy Systems and Their Application. Beijing, China: Publishing House Beijing Aeronautical Univ., 1998.
2. Z. Gao and R. E. Uhrig, "Nuclear power plant performance study by using neural networks," IEEE Trans. Nucl. Sci., vol. 39, no. 4, pp. 915-918, Aug. 1992.
3. G. Dündar and K. Rose, "The effects of quantization on multilayer neural networks," IEEE Trans. Neural Netw., vol. 6, no. 6, pp. 1446-1451, Nov. 1995.
4. C. M. Bishop, Neural Networks for Pattern Recognition. Oxford, U.K.: Clarendon, 1995.
5. J. M. Benytez, A. Blanco, M. Delgado, and I. Requena, "Neural methods for obtaining fuzzy rules," Mathw. Soft Comput., vol. 3, no. 3, pp. 371-382, 1996.
6. S. Horikawa, T. Furuhashi, S. Okuma, and Y. Uchikawa, "A fuzzy controller using a neural network and its capability to learn expert's control rules," in Proc. IIZUKA, 1990, pp. 103-106.
7. J. M. Benitez, J. L. Castro, and I. Requena, "Are artificial neural networks black boxes," IEEE Trans. Neural Netw., vol. 8, no. 5, pp. 1156-1164, Sep. 1997.
8. D. Zhang, X. Li, and K. Y. Cai, "Extended neuro-fuzzy models of multilayer perceptrons," Fuzzy Sets Syst., vol. 142, no. 2, pp. 221-242, Mar. 2004.
9. P. Yan and Z. Zhang, Neural Networks and Evolutionary Computing. Beijing, China: Press Tsinghua Univ., 2001.
10. M. E. Hoff, Jr., "Learning phenomena in network of adaptive switching circuits," Stanford Electron. Labs., Stanford, CA, Tech. Rep. 1554-1, Jul. 1962.
11. M. Stevenson, R. Winter, and B. Widrow, "Sensitivity of feedforward neural networks to weight errors," IEEE Trans. Neural Netw., vol. 1, no. 1, pp. 71-80, Mar. 1990.
12. J. Y. Choi and C. H. Choi, "Sensitivity analysis of multilayer perceptron with differentiable activation functions," IEEE Trans. Neural Netw., vol. 3, no. 1, pp. 101-107, Jan. 1992.
13. S. W. Piché, "The selection of weight accuracies for Madalines," IEEE Trans. Neural Netw., vol. 6, no. 2, pp. 432-445, Mar. 1995.
14. D. S. Yeung and X. Q. Sun, "Using function approximation to analyze the sensitivity of MLP with antisymmetric squashing activation function," IEEE Trans. Neural Netw., vol. 13, no. 1, pp. 34-44, Jan. 2002.
15. A. Y. Cheng and D. S. Yeung, "Sensitivity analysis of neocognitron," IEEE Trans. Syst., Man, Cybern. C, Appl. Rev., vol. 29, no. 2, pp. 238-249, May 1999.
16. D. S. Yeung and X. Z. Wang, "Initial analysis on sensitivity of multilayer perceptron," in Proc. IEEE SMC, 1999, vol. 3, pp. 407-411.
17. L. A. Zadeh, "Syllogistic reasoning in fuzzy logic and its application to usuality and reasoning with dispositions," IEEE Trans. Syst., Man, Cybern., vol. SMC-15, no. 6, pp. 755-763, Nov./Dec. 1985.
18. H. Madea, H. Yonekura, Y. Nonusada, and S. Murakami, "A study on the spread of fuzziness in multi-fold multi-stage approximate reasoning: An approximate reasoning using parametrical t-norm," in Proc. IEEE Int. Conf. Fuzzy Syst., Yokohama, Japan, Mar. 20-24, 1995, pp. 1455-1460.
19. H. Madea, "An investigation on the spread of fuzziness in multi-fold multi-stage approximate reasoning by pictorial representation - Under sup-min composition and triangular type membership function," Fuzzy Sets Syst., vol. 80, no. 2, pp. 133-148, Jun. 1996.
20. D. Driankov and H. Hellendoorn, "Chaining of fuzzy IF-THEN rules in Mamdani-controllers," in Proc. IEEE Int. Conf. Fuzzy Syst., Yokohama, Japan, Mar. 20-24, 1995, pp. 103-108.
21. K. Uehara and M. Fujise, "Multi-stage fuzzy inference formulated as linguistic-truth-value propagation and its learning algorithm based on back-propagation error information," IEEE Trans. Fuzzy Syst., vol. 1, no. 3, pp. 205-221, Aug. 1993.
22. F. L. Chung and J. C. Duan, "On multistage fuzzy neural network modeling," IEEE Trans. Fuzzy Syst., vol. 8, no. 2, pp. 125-142, Apr. 2000.
23. J. C. Duan and F. L. Chung, "Cascaded fuzzy neural network model based on syllogistic fuzzy reasoning," IEEE Trans. Fuzzy Syst., vol. 9, no. 2, pp. 293-306, Apr. 2001.
24. S. T. Wang, F. L. Chung, H. B. Shen, and D. W. Hu, "Cascaded centralized TSK fuzzy system: Universal approximator and high interpretation," Appl. Soft Comput., vol. 5, no. 2, pp. 131-145, 2005.
25. E. Kim, M. Park, S. Kim, and M. Park, "A transformed input-domain approach to fuzzy modeling," IEEE Trans. Fuzzy Syst., vol. 6, no. 4, pp. 596-604, Nov. 1998.
26. G. E. P. Box and G. M. Jenkins, Time Series Analysis, Forecasting and Control, 2nd ed. San Francisco, CA: Holden Day, 1976.
27. E. Kim, M. Park, S. Ji, and M. Park, "A new approach to fuzzy modeling," IEEE Trans. Fuzzy Syst., vol. 5, no. 3, pp. 328-329, Aug. 1997.
28. M. Sugeno and K. Tanaka, "Successive identification of a fuzzy model and its application to prediction of a complex system," Fuzzy Sets Syst., vol. 42, no. 3, pp. 315-334, Aug. 1991.
29. L. Wang and R. Langari, "Building Sugeno-type models using fuzzy discretization and orthogonal parameter estimation techniques," IEEE Trans. Fuzzy Syst., vol. 3, no. 4, pp. 454-458, Nov. 1995.
30. J. S. R. Jang, C. T. Sun, and E. Mizutani, Neuro-Fuzzy and Soft-Computing. Upper Saddle River, NJ: Prentice-Hall, 1997.
31. A. E. Gaweda and J. M. Zurada, "Fuzzy neural network with relational fuzzy rules," IEEE Trans. Fuzzy Syst., vol. 11, no. 1, pp. 121-134, Feb. 2003.
32. S. P. Lo and Y. Y. Lin, "The prediction of wafer surface non-uniformity using FEM and ANFIS in the chemical mechanical polishing process," J. Mater. Process. Technol., vol. 168, no. 2, pp. 250-257, Sep. 2005.