Admissibility of memorization learning with respect to projection learning in the presence of noise

IEICE Transactions on Information and Systems

Volumn E82-D, Issue 2, 1999, Pages 488-496

  Hirabayashi, Akira ^a   Ogawa, Hidemitsu ^a   Yamashita, Yukihiko ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Admissibility; Feedforward neural networks; Generalization; Over learning; Training error

Indexed keywords

ADMISSIBILITY; GENERALIZATION CAPABILITY; MEMORIZATION LEARNING; PROJECTION LEARNING; TRAINING ERROR;

ERROR CORRECTION; FEEDFORWARD NEURAL NETWORKS; FUNCTIONS; SET THEORY; SPURIOUS SIGNAL NOISE;

LEARNING SYSTEMS;

EID: 0033348109     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (14)

1. D.E. Rumelhart, J.L. McClelland, and the FDP Research Group, "Parallel Distributed Processing" vols, l and 2, MIT Press, Cambridge, 1986.
2. H. Ogawa, "Neural network learning, generalization and over-learning" Proc. Int. Conf. on Intelligent Information Processing & System, Beijing, China, vol.2, pp.1-6, Oct. 1992.
3. H. Ogawa and K. Yamasaki, "A theory of over-learning" IEICE Trans. D-II, vol.J76-D-II, no.7, pp.1280-1288, June 1993 (in Japanese). Its English version appeared in I. Aleksander and J. Taylor, ed., Artificial Neural Networks 2, vol.1, North-Holland, Amsterdam, 1992.
4. K. Yamasaki and H. Ogawa, "A theory of over-learning in the presence of noise" IEICE Trans. D-II, vol.J76-D-II, no.ll, pp.2411-2418, Nov. 1993 (in Japanese). Its English version appeared in Proc. Int. Conf. on Neural Networks '93, San Francisco, USA, pp.485-488, March 1993.
5. K. Yamasaki and H. Ogawa, "Methods for choosing a training set which prevents over-learning" IEICE Trans. D-II, vol.J76-D-II, no.ll, pp.2419-2426, Nov. 1993 (in Japanese). Its English version appeared in Proc. Int. Conf. on Neural Networks '94, Orlando, USA, pp.551-554, June 1994.
6. H. Ogawa, "Neural networks and generalization ability" IEICE Technical Report, no.NC95-8, pp.57-64, May 1995 (in Japanese).
7. S. Bergman, "The Kernel Function and Conformai Mapping" 2nd Edition, American Mathematical Society, New York, 1970.
8. Y. Yamashita and H. Ogawa, "Properties of averaged projection filter for image restoration" IEICE Trans. D-II, vol.J74-D-II, no.2, pp.142-149, Feb. 1991 (in Japanese). Its English version appeared in Systems and Computers in Japan, Scripta Technica, Inc. USA, vol.23, no.l, pp.69-78, April 1992.
9. A. Ben-Israel and T.N.E. Greville, "Generalized inverse: Theory and applications" John Wiley & Sons, New York, 1974.
10. H. Ogawa, "Projection filter regularization of illconditioned problem" Proc. of SPIE, vol.808, Inverse Problems in Optics pp. 189-196, March 1987.
11. H. Ogawa, "Neural network theory as an inverse problem" J. IEICE, vol.73, no.7, pp.690-695, July 1990 (in Japanese),
12. Y. Yamashita and H. Ogawa, "Optimum image restoration filters and generalized inverses of operators" IEICE Trans. D-II, vol.J75-D-II, no.5, pp.883-889, May 1992 (in Japanese). Its English version appeared in Systems and Computers in Japan, Scripta Technica, Inc. USA, vol.24, no.G, pp.72-81, Dec. 1993.
13. H. Ogawa and E. Oja, "Projection filter, Wiener filter, and Karhunen-Loeve subspaces in digital image restoration" J. Mathematical Analysis and Applications, vol.114, no.l, pp.37-51, Feb. 1986.
14. H. Ogawa, "Generalized sampling theorem" IEICE Trans. A, VC-1.J71-A, no.2, pp.163-170, Feb. 1988 (in Japanese), Its English version appeared in Electronics and Communications in Japan, Scripta Technica, Inc. USA, Part 3, vol.72, no.3, pp.97-105, March 1989.