Measuring and improving neural network generalization for model updating

Journal of Sound and Vibration

Volumn 238, Issue 3, 2000, Pages 401-424

  Levin, R I ^a   Lieven, N A J ^a   Lowenberg, M H ^a  

^a UNIVERSITY OF BRISTOL   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

FINITE ELEMENT METHOD; LEARNING ALGORITHMS; MATHEMATICAL MODELS; SPURIOUS SIGNAL NOISE;

JITTER; MODEL UPDATING;

NEURAL NETWORKS;

EID: 0034321211     PISSN: 0022460X     EISSN: None     Source Type: Journal    
DOI: 10.1006/jsvi.2000.3105     Document Type: Article

References (8)

1. LEVIN R. I., LIEVEN N. A. J. Dynamic finite element model updating using neural networks. Journal of Sound and Vibration. 210:1998;593-607.
2. BISHOP C. M. Neural Networks for Pattern Recognition. 1995;Oxford University Press, Oxford.
3. WATERS T. P. Finite element model updating using frequency response functions. Ph.D. Thesis, Department of Aerospace Engineering, University of Bristol, U.K. 1995.
4. SARLE W. S. Stopped training and other remedies for overfitting. Proceedings of the 27th Symposium on the Interface of Computing Science and Statistics. 1995;352-360.
5. RAFTERY A. E. MARSDEN P. V. Bayesian model selection in social research. Sociological Methodology. 1995;Blackwell, Cambridge.
6. M. J. L. ORR, 1996, Introduction to Radial Basis Function Networks, http://www.cns.ed.ac.uk/people/mark/intro.html , University of Edinburgh.
7. W. S. SARLE, 1998, Neural Network FAQ, comp.ai.neural-nets, ftp://ftp.sas.com/pub/neural/FAQ.html.
8. AN G. The effects of adding noise during backpropagation training on generalization performance. Neural Computation. 8:1996;643-674.