A new regularization learning method for improving generalization capability of neural network

Proceedings of the World Congress on Intelligent Control and Automation (WCICA)

Volumn 3, Issue , 2002, Pages 2011-2015

  Wu, Yan ^a,b   Zhang, Liming ^b  

^a TONGJI UNIVERSITY   (China)

^b FUDAN UNIVERSITY   (China)

Author keywords

Fuzzy rule inference; Generalization ability; Neural network; Regularization method

Indexed keywords

APPROXIMATION THEORY; BACKPROPAGATION; COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; FUZZY SETS; INFERENCE ENGINES; LEARNING ALGORITHMS; LEARNING SYSTEMS; MEMBERSHIP FUNCTIONS; PARAMETER ESTIMATION; PATTERN RECOGNITION;

FUZZY INFERENCE RULE; GENERALIZATION ABILITY; REGULARIZATION LEARNING;

NEURAL NETWORKS;

EID: 0036952083     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

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, CA: Morgan Kaufmann, 1992:847-854
2. Bishop C M, Neural Networks for Pattern Recognition, Oxford University Press, New York, USA, 1995
3. Saito, K, Nakano, R, Second-order learning algorithm with squared penalty term, Neural Computation, 2000, 12: 709-729
4. Aires F, Schimitt, M, Chedin, A, and Scott N, 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, 1991: 875-882
7. Chinese source 1998, 35(8): 689-693
8. Takagi H, Hayashi I, NN-driven fuzzy reasoning, Int. Journal of Approximate Reasoning, 1991, 5:191-213
9. Chinese source 1998
10. Proceedings of the 3rd World Congress on Intelligent Control and Automation, Heifei, 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
12. Rudy Setiono, Lucas Chi Kwong Hui, Use of quasi-Newton method in a feedforward neural network construction algorithm, IEEE Trans. on Neural Networks, 1995, 6(1):273-277