Active Learning in Multilayer Perceptrons

NIPS 1995: Proceedings of the 8th International Conference on Neural Information Processing Systems

Volumn , Issue , 1995, Pages 295-301

  Fukumizu, Kenji ^a  

^a RICOH COMPANY LTD   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

LEARNING SYSTEMS; MULTILAYER NEURAL NETWORKS; MULTILAYERS;

% REDUCTIONS; ACTIVE LEARNING; ACTIVE LEARNING METHODS; CRITICAL PROBLEMS; FISHER INFORMATION; HIDDEN UNITS; INFORMATION MATRIX; LEARNING TECHNIQUES; MULTILAYERS PERCEPTRONS; SINGULARITY CONDITION;

FISHER INFORMATION MATRIX;

EID: 85156219498     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. D. A. Cohn. (1994) Neural network exploration using optimal experiment design. In J. Cowan et al. (ed.), Advances in Neural Information Processing Systems 6. 679-686. San Mateo, CA: Morgan Kaufmann.
2. V. V. Fedorov. (1972) Theory of Optimal Experiments. NY: Academic Press.
3. K. Fukumizu. (1996) A Regularity Condition of the Information Matrix of a Multilayer Perceptron Network. Neural Networks, to appear.
4. K. Fukumizu, & S. Watanabe. (1994) Error Estimation and Learning Data Arrangement for Neural Networks. Proc. IEEE Int. Conf. Neural Networks:777-780.
5. K. Hagiwara, N. Toda, & S. Usui. (1993) On the problem of applying AIC to determine the structure of a layered feed-forward neural network. Proc. 1993 Int. Joint Conf. Neural Networks:2263-2266.
6. D. MacKay. (1992) Information-based objective functions for active data selection, Neural Computation 4 (4):305-318.
7. F. Pukelsheim. (1993) Optimal Design of Experiments. NY: John Wiley & Sons.
8. H. White. (1989) Learning in artificial neural networks: A statistical perspective Neural Computation l (4):425-464.