How initial conditions affect generalization performance in large networks

IEEE Transactions on Neural Networks

Volumn 8, Issue 2, 1997, Pages 448-451

  Atiya, Amir ^a   Ji, Chuanyi ^b  

^a CAIRO UNIVERSITY   (Egypt)

^b RENSSELAER POLYTECHNIC INSTITUTE   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0000036872     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.557701     Document Type: Article

References (8)

1. J. Moody, "The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems," in Advances in Neural Information Processing Systems 4, J. Moody et al., Eds. San Mateo, CA: Morgan Kaufmann, 1992.
2. S. Amari and N. Murata, "Statistical theory of learning curves under entropic loss criterion," Neural Computa., vol. 5, pp. 140-153, 1993.
3. S. Solla, "The emergence of generalization ability in learning," Advances in Neural Information Processing Systems 5. San Mateo, CA: Morgan Kaufmann, 1993.
4. A. Weigend, D. Rumelhart, and B. Huberman, "Generalization by weight elimination with application to forecasting," Advances in Neural Information Processing Systems 3. San Mateo, CA: Morgan Kaufmann, 1991.
5. Y. Abu-Mostafa, "Learning from hints in neural networks," J. Complexity, vol. 6, pp. 192-198, 1990.
6. P. Baldi and Y. Chauvin, "Temporal evaluation of generalization during learning in linear networks," Neural Computa., vol. 3, no. 3, pp. 589-603, 1991.
7. M. Polycarpou and P. Ioannou, "Learning and convergence analysis of neural-type structured networks," IEEE Trans. Neural Networks, vol. 3, pp. 39-50, 1992.
8. C. Ji, "Generalization error and the expected network complexity," Advances in Neural Information Processing Systems 5. San Mateo, CA: Morgan Kaufmann, 1993.