On the distribution of performance from multiple neural-network trials

IEEE Transactions on Neural Networks

Volumn 8, Issue 6, 1997, Pages 1507-1517

  Lawrence, Steve ^a,b   Back, Andrew D ^a,c   Tsoi, Ah Chung ^a,d,e   Giles, C Lee ^a,b,f  

^a IEEE   (United States)

^b NEC LABORATORIES AMERICA   (United States)

^c INST OF PHYS AND CHEMICAL RESEARCH   (Japan)

^d UNIVERSITY OF WOLLONGONG   (Australia)

^e UNIVERSITY OF QUEENSLAND   (Australia)

^f UNIVERSITY OF MARYLAND   (United States)

Author keywords

Backpropagation; Box whiskers; Convergence; Error analysis; Gaussian distribution; Gradient training; Kolmogorov Smirnov test; Mackey Glass; Neural networks; Phoneme classification; Probability distributions; Statistical methods

Indexed keywords

ALGORITHMS; BACKPROPAGATION; COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; ERROR ANALYSIS; LEARNING SYSTEMS; PERFORMANCE; PROBABILITY; STATISTICAL METHODS;

COMPUTATIONAL LEARNING THEORY; KOLMOGOROV-SMIRNOV TEST;

NEURAL NETWORKS;

EID: 0031276492     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.641472     Document Type: Article

References (26)

1. P. Auer, M. Herbster, and M. K. Warmuth, "Exponentially many local minima for single neurons," in Advances in Neural Information Processing Systems, D. S. Touretzky, M. Mozer, and M. Hasselmo, Eds., vol. 8. Cambridge, MA: MIT Press, 1996.
2. A. D. Back, "New techniques for nonlinear system identification: A rapprochement between neural networks and linear systems," Ph.D. dissertation, Dept. Electr. Eng., Univ. Queensland, Australia, 1992.
3. A. D. Back and A. C. Tsoi, "FIR and IIR synapses, a new neural-network architecture for time series modeling," Neural Computa., vol. 3, no. 3, pp. 375-385, 1991.
4. A. D. Back, E. Wan, S. Lawrence, and A. C. Tsoi, "A unifying view of some training algorithms for multilayer perceptrons with FIR filter synapses," in Neural Networks for Signal Processing 4, J. Vlontzos, J. Hwang, and E. Wilson, Eds. New York: IEEE Press, 1995, pp. 146-154.
5. A. L. Blum and R. L. Rivest, "Training a three-node neural network is NP-complete," Neural Networks, vol. 5, no. 1, pp. 117-127, 1992.
6. M. L. Brady, R. Raghavan, and J. Slawny, "Backpropagation fails to separate where perceptrons succeed," IEEE Trans. Circuits Syst., vol. 36, pp. 665-674, 1989.
7. R. Crane, C. Fefferman, S. Markel, and J. Pearson, "Characterizing neural-network error surfaces with a sequential quadratic programming algorithm," in Machines that Learn, Snowbird, UT, 1995.
8. C. Darken and J. E. Moody, "Note on learning rate schedules for stochastic optimization," in Advances in Neural Information Processing Systems, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds., vol. 3. San Mateo, CA: Morgan Kaufmann, 1991, pp. 832-838.
9. A. Faragó and G. Lugosi, "Strong universal consistency of neural-network classifiers," IEEE Trans. Inform. Theory, vol. 39, pp. 1146-1151, 1993.
10. J. D. Farmer, "Chaotic attractors of an infinite-dimensional dynamical system," Physica, vol. 4D, p. 366, 1982.
11. A. Flexer, "Statistical evaluation of neural-network experiments: Minimum requirements and current practice," Austrian Res. Inst. Artificial Intell., Vienna, Austria, Tech. Rep. OEFAI-TR-95-16, 1995.
12. T. G. Gonzalez, S. Sahni, and W. R. Franta, "An efficient algorithm for the Kolmogorov-Smirnov and Lilliefors tests," ACM Trans. Math. Software, vol. 3, no. 1, pp. 60-64, 1977.
13. S. Haykin, Neural Networks, A Comprehensive Foundation. New York: Macmillan, 1994.
14. B. A. Huberman, R. M. Lukose, and T. Hogg, "An economics approach to hard computational problems," Science, vol. 275, pp. 51-54, 1997.
15. J. S. Judd, "On the complexity of loading shallow neural networks," J. Complexity, vol. 4, pp. 177-192, 1988.
16. _, Neural-Network Design and the Complexity of Learning. Cambridge, MA: MIT Press, 1990.
17. S. Lawrence, C. L. Giles, and A. C. Tsoi, "Lessons in neural-network training: Overfitting may be harder than expected," in Proc. 14th Nat. Conf. Artificial Intell., AAA-97. Menlo Park, CA: AAAI Press, 1997, pp. 540-545.
18. J. H. Lin and J. S. Vitter, "Complexity results on learning by neural nets," Machine Learning, vol. 6, pp. 211-230, 1991.
19. M. C. Mackey and L. Glass, "Oscillation and chaos in physiological control systems," Science, vol. 197, p. 287, 1977.
20. A. Papoulis, Probability, Random Variables, and Stochastic Processes, 3rd ed. New York: McGraw-Hill, 1991.
21. W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery, Numerical Recipes, 2nd ed. Cambridge, U.K.: Cambridge Univ. Press, 1992.
22. J. W. Tukey, Exploratory Data Analysis. Reading, MA: Addison-Wesley, 1977.
23. M. Verleysen, J. L. Voz, P. Thissen, and J. D. Legat, "A statistical neural network for high-dimensional vector classification," in Proc. IEEE Int. Conf. Neural Networks, ICNN'95, Perth, Western Australia, 1995.
24. R. von Mises, Mathematical Theory of Probability and Statistics. New York: Academic, 1964.
25. A. S. Weigend and N. A. Gershenfeld, "Results of the time series prediction competition at the Santa Fe Institute," in IEEE Int. Conf. Neural Networks. Piscataway, NJ: IEEE Press, 1993, pp. 1786-1793.
26. N. A. Weiss and M. J. Hassett, Introductory Statistics, 2nd ed. Reading, MA: Addison-Wesley, 1987.