Neural network dimension selection for dynamical system identification

Proceedings of the IEEE International Conference on Control Applications

Volumn , Issue , 2008, Pages 972-977

  Sabo, Devin ^a,b   Yu, Xiao Hua ^a  

^a CALIFORNIA POLYTECHNIC STATE UNIVERSITY   (United States)

^b Lockheed Martin Corporation   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPLICATIONS; ARTIFICIAL INTELLIGENCE; BOOLEAN FUNCTIONS; COMPUTATIONAL METHODS; COMPUTER NETWORKS; COMPUTER SIMULATION; DYNAMICAL SYSTEMS; FEEDFORWARD NEURAL NETWORKS; IDENTIFICATION (CONTROL SYSTEMS); IMAGE CLASSIFICATION; NETWORK PROTOCOLS; RADIAL BASIS FUNCTION NETWORKS; SCHRODINGER EQUATION; SENSOR NETWORKS; VEGETATION;

CLASSIFICATION ACCURACIES; CONTROL APPLICATIONS; HYBRID NEURAL NETWORK; INTERNATIONAL CONFERENCES; MULTI-LAYER FEED-FORWARD NEURAL NETWORKS; NETWORK DIMENSIONING; NEURAL NETWORK APPLICATIONS; OPTIMAL SOLUTIONS; PATTERN CLASSIFICATION PROBLEMS; SIMULATION RESULTS; SYSTEM IDENTIFICATION;

NEURAL NETWORKS;

EID: 53349120885     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CCA.2008.4629704     Document Type: Conference Paper

References (15)

1. Fnaiech, N., Abid, S., Fnaiech, F., and Cheriet, M., "A modified version of a formal pruning algorithm based on local relative variance analysis", First International Symposium on Control, Communications and Signal Processing (2004), pp.849-852
2. Abid, S., Fnaiech, F., and Najim, M., "A fast Feed-Forward Training Algorithm Using a Modified Form of the Standard Back-Propagation Algorithm", IEEE Transactions on Neural Network (2001), Volume 12, Issue 2, pp.424-430.
3. Andrews, R., Diederich, J., Golea, M., and Tickle, A.B., "The truth will come to light: Directions and challenges in extracting knowledge embedded within trained artificial neural networks", IEEE Transactions on Neural Networks (1998), Volume 9, Issue 6, pp. 1057-1068.
4. Blake, E. K. C. and Merz, C., "UCI repository of machine learning databases", University of California, Irvine, Department of Information and Computer Science, 1998.
5. Efe, M.O., Iplikci, S., Kayank, O., and Wilamowski, B., "An Algorithm for Fast Convergence in Training Neural Networks", International Joint Conference on Neural Networks, pp. 1778-1782, Washington DC, July 15-19, 2001.
6. Engelbrecht, A.P., "A new pruning heuristic based on variance analysis of sensitivity information", IEEE Transactions on Neural Networks (2001), Volume 12, Issue 6, pp.1389-1399.
7. Giles, C.L. and Lawrence, S., "Overfitting and Neural Networks: Conjugate Gradient and Backpropagation", Proceedings of the IEEE International Conference on Neural Networks (2000), pp.114-119.
8. Haykin, S., "Neural networks: a comprehensive foundation," Upper Saddle River, N.J., Prentice Hall, 1999.
9. Huynh, T.Q. and Setiono, R., "Effective neural network pruning using cross-validation", IEEE International Joint Conference on Neural Networks (2005), Volume 2, pp.972-977.
10. Karnin, E.D., "A simple procedure for pruning back-propagation trained neural networks", IEEE Transactions on Neural Networks (1990), Volume 1, Issue 2, pp.239-242.
11. Marsland, S., Nehmzow, S.U., and Shapiro, J., "A self-organizing network that grows when required", in Neural Networks, Volume 15 (2002), Isuue 8-9, pp.1041-1058.
12. Mozer, M. C. and Smolensky, P., "Skeletonization: A technique for trimming the fat from a network via relevance assessment," in Advances in Neural Information Processing (1989), D.S. Touretzky, Ed., pp.107-115.
13. Ponnapalli, P.V.S., Ho, K.C., and Thomson, M., "A formal selection and pruning algorithm for feedforward artificial neural network optimization", IEEE Transactions on Neural Networks (1999), Volume 10, Issue 4, pp.964-968.
14. Fnaiech, N., Fnaiech, F., and Cheriet, M., "A new feedforward neural network pruning algorithm: SSM-iterative pruning (SSMIP)", IEEE International Conference on Systems, Man and Cybernetics (2002)
15. Fnaiech, F., Fnaiech, N., and Najim, M., "A new feedforward neural network hidden layer neuron pruning algorithm", IEEE International Conference on Acoustics, Speech, and Signal (2001), pp. 1277-1280.