A NOVEL NEURAL NETWORK LEARNING METHOD OF DYNAMICALLY TUNING REGULARIZATION COEFFICIENT ACCORDINT TO FUZZY RULES

[in Chinese]; [in Chinese]

[1] Moody J E. The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems. In: Advances in Neural Information Processing Systems 4, San Mateo: Morgan Kaufmann, 1992, 847-854

[2] Bishop C M. Neural Networks for Pattern Recognition, New York: Oxford University Press: USA,1995

[3] Saito K, Nakano R. Second-order learning algorithm with squared penalty term. Neural Computation, 2000,12:709-729

[4] Aires F, Schmitt M, Chedin A, et al. The "weight smoothing" regulation of MLP for Jacobian stabilization. IEEE Trans. on Neural Networks, 1999,10(6):1502-1510

[5] Ishikawa M. Structural learning with forgetting. Neural Networks, 1996,9(3):509-521

[6] Weigend A S, Rumelhart D E, Huberman B A. Generalization by weight-elimination with application to forecasting. In: Advances in Neural Information Processing Systems, San Mateo: Morgan Kaufmann,1991,875-882

[8] Takagi H, Hayashi I、 NN-driven fuzzy reasoning. Int. Journal of Approximate Reasoning, 1991,5:191-213

[10] LI Dong-Mei, LIU Jun-Qiang, HU Heng-Zhang. A fast algorithm for training a class of fuzzy neural networks.in: Proceedings of the 3rd World Congress on Intelligent Control and Automation, Hefei, China,2000,Vol.2:852-856

[11] Shi Y H, Eberhart R, Chen Y B. Implementation of evolutionary fuzzy systems. IEEE Trans. on Fuzzy Systems, 1999,7(2):109-119