An active learning algorithm based on existing training data

IEICE Transactions on Information and Systems

Volumn E83-D, Issue 1, 2000, Pages 90-99

  Takizawa, Hiroyuki ^a   Nakajima, Taira ^a   Kobayashu, Hiroaki ^a   Nakamura, Tadao ^a  

^a TOHOKU UNIVERSITY   (Japan)

Author keywords

Active learning; Classification problems; Multilayer perceptrons; The network inversion algorithm

Indexed keywords

DATA REDUCTION; DATA STRUCTURES; LEARNING ALGORITHMS; LEARNING SYSTEMS;

ACTIVE LEARNING ALGORITHMS; NETWORK INVERSION ALGORITHMS;

MULTILAYER NEURAL NETWORKS;

EID: 0033903165     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (20)

1. D.E. Rumelhart, G.E. Hinton, and R.J. Williams, Learning representations by back-propagating errors, Nature, vol.323, pp.533-530, 1986.
2. L. Prcclielt, PROBEN1 - A sot of benchmarks and benchmarking rules for neural network training algorithms, Technical report, Fakultät für Informatik, Universität Karlsruhe, number 21/91, 1991.
3. L.P. Cordella, C. De Stefano, F. Tortorella, and M. Vento, A method for improving classification reliability of multilayer perceptrons, IEEE Trans. Neural Networks, vol.6, no.5, pp.140-1147, 1995.
4. S.B. Clio, Neural-network classifiers for recognizing totally unconstrained handwritten numerals, IEEE Trans. Neural Networks, vol.8, no.l, 1997.
5. F. Leisch, L.C. Jain, and K. Hornik, Cross-validation with active pattern selection for neural-netowrk classifiers, IEEE Trans. Neural Networks, vol.9, no.l, 1998.
6. E. Baum, Neural nets that learn in polynomial time from examples and queries, IEEE Trans. Neural Networks, vol.2, no.l, 1991.
7. D. MacKay, Information-based objective functions for active data selection, Neural Computation, vol.4, pp.590604, 1992.
8. D. Cohn, Z. Ghahramani, and M. Jordan, Active learining with statistical models, Advances in Neural Processing Systems, vol.7, pp.705-712, 1995.
9. D. Cohn, Neural network exploration using optimal experiment design, Neural Networks, vol.9, 1996.
10. D. Cohn, Minimizing statistical bias with queries, Advances in Neural Information Processing Systems, vol.9, 1997.
11. J. Hwang, J. Choi, S. Oh, and R.J. Mark II, Querybased learning applied to partially trained multilayer perceptrons, IEEE Trans. Neural Networks, vol.2, no.l, 1991.
12. Y. Freund, U.S. Seung, E. Shamir, and N. Tishby, Information, prediction, and query by committee, Advances in Neural Information Processing Systems, vol.5, 1993.
13. L. Atlas, D. Cohn, and R. Ladner, Training connectionist networks with queries and selective sampling, Advances in Neural Information Processing Systems, vol.2, pp.566-573, 1990.
14. C. Lee and D.A. Landgrebe, Decision boundary feature extraction for neural networks, IEEE Trans. Neural Networks, vol.8, no.l, pp.75-83, 1997.
15. S.E. Fahlman, An empirical study of learning speed in back-propagation networks, Technical Report, CMU, number CMU-CS-88-162, 1988.
16. C.W. Lee, Training feedforward neural networks: An algorithm giving improved generalization, Neural Networks, vol.10, no.l, pp.61-68, 1997.
17. M. Ricdmiller and H. Braun, A direct adaptive method for faster backpropagation learning: The RPROP algorithm, Proc. IEEE International Conference on Neural Networks, San Francisco, CA, 1993.
18. E.B. Baum and D. Haussler, ''What size net gives valid generalization?, Advances in Neural Information Processing System, vol.1, 1989.
19. D. Sarkar, Randomness in generalization ability: a source to improve it, IEEE Trans. Neural Networks, vol.7, no.3, pp.676-685, 1996
20. H. Takizawa, T. Nakajima, M. Nishi, H. Kobayashi, and T. Nakamura, Acceleration techniques for the network inversion algorithm, IEICE Trans. Inf. fc Syst., vol.E82-D, no.2, Feb. 1909.