Nonmonotonic generalization bias of gaussian mixture models

Neural Computation

Volumn 12, Issue 6, 2000, Pages 1411-1427

  Akaho, Shotaro ^a   Kappen, Hilbert J ^b  

^a ELECTROTECHNICAL LABORATORY   (Japan)

^b RADBOUD UNIVERSITY NIJMEGEN   (Netherlands)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER SIMULATION; LEARNING; NORMAL DISTRIBUTION; TEMPERATURE;

COMPUTER SIMULATION; LEARNING; NEURAL NETWORKS (COMPUTER); NORMAL DISTRIBUTION; TEMPERATURE;

EID: 0034202524     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976600300015439     Document Type: Article

References (17)

1. Amari, S. (1993). A universal theorem on learning curves. Neural Networks, 6, 161-166.
2. Barkai, N., Seung H. S., & Sompolinsky, H. (1993). Scaling laws in learning of classification tasks. Physical Review Letters, 70, 3167-3170.
3. Bezdek, J. C. (1980). A convergence theorem for the fuzzy ISODATA clustering algorithms. IEEE Trans. on PAMI, 2, 1-8.
4. Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. J. Royal Statistical Soc. Ser. B, 39, 1-38.
5. Jacobs, R. A., & Jordan, M. I. (1991). A competitive modular connectionist architecture. In D. Touretzky & R. Lippmann (Eds.), Advances in neural information processing systems, 3 (pp. 767-773). San Mateo, CA: Morgan Kaufmann.
6. Jordan, M. I., & Jacobs, R. A. (1994). Hierarchical mixtures of experts and the EM algorithm. Neural Computation, 6, 181-214.
7. Kappen, B. (1993). Using Boltzmann machines for probability estimation: A general framework for neural network learning. In S. Gielen et al. (Eds.), Proc. of ICANN'93 (pp. 521-526). Berlin: Springer-Verlag.
8. Kappen, B. (1995). Deterministic learning rules for Boltzmann machines. Neural Networks, 8, 537-548.
9. Moody, J. (1992). The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems. In J. E. Moody, S. J. Hanson, & R. P. Lippman (Eds.), Advances in neural information processing systems, 4 (pp. 847-854). San Mateo, CA: Morgan Kaufmann.
10. Murata, N., Yoshizawa, S., & Amari, S. (1991). A criterion for determining the number of parameters in an artificial neural network model. In T. Kohonen et al. (Eds.), Artificial neural network (ICANN) (pp. 9-14). Amsterdam: Elsevier.
11. Murata, N., Yoshizawa, S., & Amari, S. (1994). Network information criterions -determining the number of parameters for an artificial neural network model. IEEE Trans. on Neural Networks, 5, 865-872.
12. Nijman, M. J., & Kappen, H. J. (1997). Symmetry breaking and training from incomplete data with radial basis Boltzmann machines. International Journal of Neural Systems, 8, 301-316.
13. Poggio, T., & Girosi, F. (1990). Networks for approximation and learning. Proceedings of the IEEE, 78, 1481-1497.
14. Rissanen, J. (1986). Stochastic complexity and modeling. Annals of Statistics, 14, 1080-1100.
15. Rose, K., Gurewitz, E., & Fox, G. (1990). Statistical mechanics of phase transitions in clustering. Physical Review Letters, 65, 945-948.
16. Titterington, D. M. (1985). Statistical analysis of finite mixture distribution. New York: Wiley.
17. Vapnik, V. A. (1984). Estimation of dependences based on empirical data. New York: Springer-Verlag.