Partially connected feedforward neural networks structured by input types

IEEE Transactions on Neural Networks

Volumn 16, Issue 1, 2005, Pages 175-184

  Kang, Sanggil ^a   Isik, Can ^b  

^a Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

^b SYRACUSE UNIVERSITY   (United States)

Author keywords

Fully connected neural network (FCNN); Input sensitivity; Input type (IT); Partially connected neural network (PCNN)

Indexed keywords

LEARNING ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; SENSITIVITY ANALYSIS;

FULLY CONNECTED NEURAL NETWORK; INPUT SENSITIVITY; INPUT TYPE; PARTIALLY CONNECTED NEURAL NETWORK;

FEEDFORWARD NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; ARTIFICIAL NEURAL NETWORK; AUTOMATED PATTERN RECOGNITION; CLUSTER ANALYSIS; COMPARATIVE STUDY; COMPUTER ANALYSIS; COMPUTER SIMULATION; EVALUATION; FEEDBACK SYSTEM; INFORMATION RETRIEVAL; MATHEMATICAL COMPUTING; METHODOLOGY; SIGNAL PROCESSING; STATISTICAL MODEL;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; CLUSTER ANALYSIS; COMPUTER SIMULATION; COMPUTING METHODOLOGIES; FEEDBACK; INFORMATION STORAGE AND RETRIEVAL; MODELS, STATISTICAL; NEURAL NETWORKS (COMPUTER); NUMERICAL ANALYSIS, COMPUTER-ASSISTED; PATTERN RECOGNITION, AUTOMATED; SIGNAL PROCESSING, COMPUTER-ASSISTED;

EID: 13844298048     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2004.839353     Document Type: Article

References (27)

1. M. Mangeas, A. S. Weigend, and C. Muller, "Forecasting electricity demand using nonlinear mixture of experts," in Proc. World Congr. Neural Networks, vol. 2, 1995, pp. 48-53.
2. D. M. Bates, Nonlinear Regression Analysis and its Applications. New York: Wiley, 1998.
3. D. Cohen and J. Shawe-Taylor, "Feedforward networks-a tutorial," in Proc. Meeting Neural Computing, 1989, pp. 1-13.
4. N. Petkov, "Systolic simulation of multilayer, feed-forward neural networks," Parallel Process. Neural Syst. Comput., pp. 303-306, 1990.
5. L. Mussone, "A review of feed-forward neural networks in transportation research," Elektrotechnik und Informationstechnik, vol. 116, no. 6, pp. 360-365, 1999.
6. H. Mori, K. Itou, H. Uematsu, and S. Tsuzuki, "An artificial neural net based method for predicting power system voltage harmonics," IEEE Trans. Power Del., vol. 7, no. 1, pp. 402-409, Jan. 1992.
7. Y. Le Cun, J. S. Denker, and S. A. Solla, "Optimal brain damage," Adv. Neural Inform. Process. Syst., vol. 2, pp. 598-605, 1990.
8. B. Hassibi, D. G. Stork, and C. Wolff, "Optimal brain surgeon: Extensions and performance comparisons," Adv. Neural Inform. Process. Syst., vol. 6, pp. 263-270, 1994.
9. D. E. Duckro, D. W. Quinn, and S. J. Gardner, "Neural network pruning with Tuckey Kramer multiple comparison procedure," Neural Computat. vol. 14, pp. 1149-1168, 2002.
10. E. D. Karnin, "A simple procedure for pruning backpropagation trained neural netwowrks," IEEE Trans. Neural Netw., vol. 1, no. 2, pp. 239-242, Jun. 1990.
11. J. Sietsma and R. J. F. Dow, "Neural net pruning- why and how," in Proc. IEEE Int. Conf. Neural Networks, vol. 1, 1988, pp. 325-333.
12. S. Viaene, B. Baesens, G. Dedene, J. Vanthienen, and J. Vandenbulcke, "Sensitivity based pruning of input variables by means of weight cascaded training," in Proc. PADD, 2000, pp. 141-159.
13. A. H. Rambhia, R. Glenny, and J. N. Hwang, "Critical input data channels selection for progressive work exercise test by neural network sensitivity snalysis," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing, 1999, pp. 1097-1100.
14. A. H. Sung, "Ranking input importance in neural network modeling of engineering problems," in Proc. IEEE Int. Joint Conf. Neural Network 1998, pp. 316-321.
15. B. Efron and R. Tibshirani, An Introduction to the Bootstrap. London, U.K.: Chapman & Hall, 1998.
16. J. L. Noyes, B3.5 Handbook of Neural Computation. London, U.K.: Chapman & Hall, 1997.
17. D. Elizondo and E. Fiesler, "A survey of partially connected neural networks," Int. J. Neural Syst., vol. 8, no. 5 and 6, pp. 535-558, 1997.
18. E. Fiesler, "Comparative bibliography of onto-genic neural networks," in Proc. Int. Conf. Artificial Neural Networks, 1994, pp. 793-796.
19. D. Elizondo, E. Fiesler, and J. Korczak, "Non-ontogenic sparse neural networks," in Proc. Int. Conf. Neural Networks, 1995, pp. 290-295.
20. Y. Y. Chung, M. T. Wong, and N. W. Bergmann, "High-speed neural network based classifier for real-time application," in Proc. ICSP '98, pp. 506-509.
21. A. Rajapakse, K. Furuta, and S. Kondo, "Identification of nonlinear dynamic models with particially connected neural networks trained using orthogonal least square estimation," Trans. Inst. Electr. Eng. Japan vol. 3, pp. 335-343, 1999.
22. I. K. Sethi, "Entropy nets: From decision trees to neural networks," Proc. IEEE, vol. 78, no. 3, pp. 1605-1613, Mar. 1990.
23. J. M. Zurada, A. Malinowski, and U. Shiro, "Perturbation method for deleting redundant input of perceptron networks," Neurocomput., vol. 14, no. 2, pp. 177-193, 1996.
24. G. F. Wyeth, G. Buskey, and J. Roberts, "Flight control using an artificial neural network," in Proc. Australian Conf. Robotics and Automation, 2000, pp. 65-70.
25. J. Chen and S. M. Kang, "Model-order reduction of weekly nonlinear MEMS devices with Taylor series amplification and Arnoldi process," in Proc. 43rd IEEE Midwest Symp. Circuits and Systems, 2000, pp. 248-251.
26. Welch-Allyn: A Medical Instrument Product Company [Online]. Available: www.welchallyn.com
27. J. G. Webster, Medical Instrumentation:Application and Design, 3rd ed. New York: Wiley, 1993.