Rapid discriminative learning based on misclassification measure

Systems and Computers in Japan

Volumn 37, Issue 3, 2006, Pages 58-68

  Rokui, Jun ^a,b,c  

^a SHIMANE UNIVERSITY   (Japan)

^b IEEE   (Japan)

^c Human Interface Society   (Japan)

Author keywords

Generalization ability; Generalized Probabilistic Descent (GPD); Minimum Classification Error (MCE); Overtraining; Regularization

Indexed keywords

GENERALIZATION ABILITY; GENERALIZED PROBABILISTIC DESCENT (GPD); MINIMUM CLASSIFICATION ERROR (MCE); OVERTRAINING; REGULARIZATION;

CLASSIFICATION (OF INFORMATION); DATA REDUCTION; ERROR ANALYSIS; ERROR DETECTION; PROBLEM SOLVING; SPEECH RECOGNITION; VECTORS;

LEARNING SYSTEMS;

EID: 33644891893     PISSN: 08821666     EISSN: 1520684X     Source Type: Journal    
DOI: 10.1002/scj.20353     Document Type: Article

References (25)

1. Amari S. A theory of adaptive pattern classifiers. IEEE Trans EC 1967;16:299-307.
2. Juang B-H, Katagiri S. Discriminative learning for minimum error classification. IEEE Trans Signal Process 1992;40(12).
3. Kurosawa Y. Probabilistic descent method applied to similarity and discrepancy of quadratic form for pattern recognition. Tech Rep IEICE 1997;PRMU97-181.
4. Rabiner L, Jung B-H. Fundamentals of speech recognition. PTR Prentice-Hall; 1993.
5. Chou W, Lee C-H, Juang B-H. Minimum error rate training of inter-word context dependent acoustic model units in speech recognition. Proc ICASSP94, II-652-655.
6. Yonezawa Y, Akagi M. Modeling of contextual effects based on the minimum classification error criterion. Tech Rep IEICE 1994;SP94-114.
7. MacDermott E, Katagiri S. Prototype-based minimum classification error/generalized probabilistic descent training for various speech units. Computer Speech and Language, p 351-368, Aug 1994.
8. Takahashi J, Sagayama S. An efficient HMM learning method for a small amount of data using minimum classification error. Tech Rep IEICE 1995;SP95-103.
9. Uemoto N, Matsuoka T, Matsui T, Furui S. Detection of an acoustic model learning method in connected digit speech recognition. Trans Acoust Soc Japan, 1-Q-13, 121-122, 1995.
10. Schapire R, Freund Y, Barlett P. Boosting the margin: A new explanation for the effectiveness of voting methods. Ann Statist 1998;26:1651-1686.
11. Breiman L. Bagging predictors. Machine Learning 1996;24:123-140.
12. Vapnik VN. Statistical learning theory. Wiley; 1998.
13. Rätsch G, Onoda T, Müller KR. Soft margin for adaboost. Machine Learning 2001;42:287-320.
14. Mitchell TM. Version spaces: An approach to concept learning. Stanford Technical Report STAX CS, Vol. 78, No. 711, p 79-92, 1978.
15. Kita H. Generalization ability of neural networks. J Inst Syst Control Inf Eng 1992:36:625-633.
16. Ogawa H. Neural networks and generalization ability. Tech Rep IEICE 1995;NC95-8.
17. Bishop CM. Curvature-driven smoothing: A learning algorithm for feed-forward networks. IEEE Trans Neural Networks 1993;4:882-884.
18. Tikhonov AN, Goneharsky AV, Stepanov VV, Yagola AG. Numerical methods for the solution of ill-posed problems. Kluwer Academic Publishers; 1990.
19. Tikhonov AN, Arsenin V Y. Solutions of ill-posed problems. V.H. Winston; 1977.
20. Bishop CM. Neural networks for pattern recognition. Oxford University Press; 1995.
21. Watanabe E. A learning algorithm for improving generalization ability of multi layered neural networks for pattern recognition problem. Trans IEICE 1996;J79-D-II:917-923.
22. Watanabe E. A learning algorithm for improving generalization ability of multi layered neural networks for function approximation problems. Trans IEICE 1996;J79-D-II:924-931.
23. Ishikawa M. Structural learning using connectionist model forgetting. Tech Rep IEICE 1988;MBE88-144.
24. Haga T, Ishikawa M. Comparison of structure creation and generalization ability of various types of structural learning methods. Tech Rep IEICE 1993;NC93-20.
25. Kimura Y. Learning algorithm for minimizing error and output variation and its application to recognition of distorted handwritten kanji. Trans IEICE 1990;J73-D-II:840-847.