Sensitivity analysis of neocognitron

IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

Volumn 29, Issue 2, 1999, Pages 238-249

  Cheng, Antony Y ^a   Yeung, Daniel S ^a  

^a HONG KONG POLYTECHNIC UNIVERSITY   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; DATA STORAGE EQUIPMENT; ERRORS; MATHEMATICAL MODELS; PATTERN RECOGNITION; PERTURBATION TECHNIQUES; SENSITIVITY ANALYSIS; SPURIOUS SIGNAL NOISE;

INPUT DEVICES; MADALINE MODEL; NEOCOGNITRON;

COGNITIVE SYSTEMS;

EID: 0032630954     PISSN: 10946977     EISSN: None     Source Type: Journal    
DOI: 10.1109/5326.760568     Document Type: Article

References (32)

1. A. Y. T. Cheng, "Sensitivity analysis and performance tuning of neocognitron," M.Phil, thesis, Hong Kong Polytechnic Univ., Hong Kong, Oct. 1996.
2. J. Y. Choi and C.-H. Choi, "Sensitivity analysis of multilayer perceptron with differentiable activation functions," IEEE Trans. Neural Networks, vol. 3, pp. 101-107, Jan. 1992.
3. M.-Y. Chow and S. O. Yee, "A measure of relative robustness for feedforward neural networks subject to small input perturbations," Int. J. Neural Syst., vol. 3, no. 3, pp. 291-299, 1992.
4. R. K.-L. Chun, "Fault-tolerance characteristics of neural networks," Ph.D. dissertation, Univ. Calif., Los Angeles, 1989.
5. D. F. Cook and R. E. Shannon, "A sensitivity analysis of a backpropagation neural network for manufacturing process parameters," J. Intell. Manufact., vol. 2, pp. 155-164, 1991.
6. G. W. Davis, "Sensitivity analysis in neural net solution," IEEE Trans. Syst., Man, Cybern., vol. 19, pp. 1078-1082, Sept./Oct. 1989.
7. L. Fu and T. Chen, "Sensitivity analysis for input vector in multilayer feedforward neural networks," in IEEE Int. Conf. Neural Networks, 1993, vol. 1, pp. 215-218.
8. K. Fukushima, "Neocognitron: A hierarchical neural network capable of visual pattern recognition," Neural Networks, vol. 1, pp. 119-130, 1988.
9. _, "Analysis of the process of visual pattern recognition by the neocognitron," Neural Networks, vol. 2, pp. 413-420, 1989.
10. _, "Character recognition with neural networks," Neurocomputing, vol. 4, pp. 221-233, 1992.
11. _, "Improvement of the neocognitron and the selective attention model," in World Congr. Neural Networks, July 1993, vol. 3, pp. 634-637.
12. K. Fukushima, K. Nagahara, H. Shouno, and M. Okada, "Training neocognitron to recognize handwritten digits in the real world," in World Congr. Neural Network San Diego, CA, 1996, pp. 21-24.
13. K. Fukushima, S. Miyake, and T. Ito, "Neocognitron: A neural network model for mechanism of visual pattern recognition," IEEE Trans. Syst., Man, Cybern., vol. SMC-13, pp. 826-834, Sept./Oct. 1983.
14. K. Fukushima and N. Wake, "Handwritten alphanumeric character recognition by the neocognitron," IEEE Trans. Neural Networks, vol. 2, pp. 355-365, May 1991.
15. F. H. Glanz, "Statistical extrapolation in certain adaptive pattern-recognition systems," Ph.D. dissertation, Stanford Univ., Stanford, CA, May 1965.
16. M. M. Gow, A Course in Pure Mathematics, 1st ed. New York: Hodder and Stoughton, 1960.
17. Z. Guo and R. E. Uhrig, "Nuclear power plant performance study by using neural networks," IEEE Trans. Nucl. Sci., vol. 39, no. 4, pp. 915-918, 1992.
18. N. R. P. J. Basak and S. K. Pal, "A connectionist system for learning and recognition of structures: Application to handwritten characters," Neural Networks, vol. 8, no. 4, pp. 643-657, 1995.
19. L. C. Jiao and Z. Bao, "Neural networks via nonlinear sensitivity approach," in IEEE Int. Symp. Circuits Systems, 1991, vol. 5, pp. 2542-2545.
20. P. M. Lin, "Sensitivity analysis of large linear networks using symbolic programs," in IEEE Int. Symp. Circuits Systems, 1992, vol. 3, pp. 1145-1148.
21. D. R. Lovell, "The neocognitron as a system for handwritten character recognition: Limitations and improvements," Ph.D. dissertation, Univ. Queensland, Queensland, Australia, July 1994.
22. M. T. Musavi, K. H. Chan, D. M. Hummels, and K. Kalantri, "On the generalization ability of neural network classifiers," IEEE Trans. Pattern Anal. Machine Intell., vol. 16, pp. 659-663, June 1994.
23. S.-H. Oh and Y. Lee, "Sensitivity analysis of single hidden-layer neural networks with threshold functions," IEEE Trans. Neural Networks, vol. 6, pp. 1005-1007, July 1995.
24. S. Oh and R. J. Marks II, "Noise sensitivity of projection neural networks," in IEEE Int. Symp. Circuits Systems, 1989, vol. 3, pp. 2201-2204.
25. A. N. Refenes, A. Zapranis, and G. Francis, "Stock performance modeling using neural networks: A comparative study with regression models," Neural Networks, vol. 7, no. 2, pp. 375-388, 1994.
26. M. Stevenson, R. Winter, and B. Widrow, "Sensitivity of feedforward neural networks to weight errors," IEEE Trans. Neural Networks, vol. 1, pp. 71-80, Mar. 1990.
27. F. G. Stremler, Introduction to Communication Systems, 3rd ed. Reading, MA: Addison-Wesley, 1990.
28. B. A. White and M. I. Elmasry, "The digi-neocognitron: A digital neocognitron neural network model for VLSI," IEEE Trans. Neural Networks, vol. 3, pp. 73-85, Jan. 1992.
29. B. Widrow, "Adaptive switching circuits," in IREWESCON Convention Record, New York, Sept. 1960, pp. 96-104.
30. R. G. Winter, "Madaline rule II: A new method for training networks of adalines," Ph.D. dissertation, Stanford Univ., Stanford, CA, Jan. 1989.
31. Y. Xie and M. A. Jabri, "Analysis of the effects of quantization in multilayer neural networks using a statistical model," IEEE Trans. Neural Networks, vol. 3, pp. 334-338, Mar. 1992.
32. Q. Xu, C. Jurgens, and B. Arrue, "A fault tolerance analysis of a neocognitron model," in Int. Joint Conf. Neural Networks, Washington DC, Jan. 1990, vol. 2, pp. 559-562.