Evolution and generalization of a single neurone II. Complexity of statistical classifiers and sample size considerations

 RAUDYS Sarunas
 Institute of Mathematics and Informatics
Search this Article
Author(s)

 RAUDYS Sarunas
 Institute of Mathematics and Informatics
Journal

 Neural Networks

Neural Networks 11(2), 297313, 19980301
References: 58

1
 On expected probability of misclassification of zero empirical error classifier

BASALYKAS A.
Vilnius 7(2), 137154, 1996
Cited by (1)

2
 On expected probability of misclassification of zero empirical error classifier

BASALYKAS A.
Vilnius 8(2), 310311, 1997
Cited by (1)

3
 Learning curves of online and offline training

BOS S.
Proc. ICANN'96, 1996
Cited by (1)

4
 Geometrical and statistical properties of systems of linear inequalites with applications in pattern recognition

COVER T. M.
IEEE Tran. Elec. Comp EC14, 325334, 1965
Cited by (1)

5
 Representation of statistics of discriminant analysis and asymptortic expansions in dimensionalities comparable with sample size

DEEV A. D.
Reports of Ac. of Sci. of The USSR 195(4), 756762, 1970
Cited by (1)

6
 Asymptotic expansions for distributions of statistics W, M, W〜* in discriminant analysis

DEEV A. D.
Statistical Methods of Classification 31, 657, 1972
Cited by (1)

7
 Discrimiant function designed on independent blocks of variables

DEEV A. D.
Engineering Cybernetics, USSR J. 12, 153156, 1974
Cited by (1)

8
 Measurement selection for linear discrimiant used in pattern classification

ESTES S. E.
Ph. D. dissertation, Standford University, 1965
Cited by (1)

9
 Statistical theory of learning a rule

GYORGYI G.
Neural Networks and Spin Glasses, 3136, 1990
Cited by (1)

10
 Rigorous learning curves from statistical mechanics

HAUSSLER D.
Proc. 7th Annual ACM Conf. on Comput. Learning Theory, 7687, 1994
Cited by (1)

11
 On dimensionality and sample size in statistical pattern classification

KANAL L.
Pattern Recognition 3, 238255, 1971
Cited by (2)

12
 <no title>

KHARIN Yu. S.
Robustness in Statistical Pattern Recognition, 1992
Cited by (1)

13
 A simple weight decay can improve generalization.

KROGH A.
Advances in neural information processing 4, 950957, 1992
Cited by (2)

14
 A statistical approach to generalization in layered neural networks

LEVIN E.
Proceedings of the IEEE 78, 21332150, 1990
Cited by (1)

15
 On representativeness of the sample size while choosing the effective measurement system

LBOV G. S.
Computing systems, Issue 22, 3958, 1966
Cited by (1)

16
 Assignment of nemerical values to nominal variables

MESHALKIN L. D.
Statistical methods of control, Issue 14, 4956, 1976
Cited by (1)

17
 Calculation of the learning curve of Bayes optimal classification algorithm for learning perceptron with noise

OPPER M.
Proc. 4th Annual ACM Conf. on Comput. Learning Theory, 7587, 1991
Cited by (1)

18
 Analysis of learning speed of three linear classifers

PIKELIS V.
Ph. D. dissertation, Inst. of Physics and Mathematics, 1136, 1974
Cited by (1)

19
 Comparison of methods of computing the expected classification errors

PIKELIS V.
Engineering Cybernetics (USSR J. ) N5, 5963, 1976
Cited by (1)

20
 On some problems arising of discrimination with multiple characters

RAO C. R.
Sankya 9, 343365, 1949
Cited by (1)

21
 On determining the training sample size of a linear classifier

RAUDYS S.
Computing systems 28, 7987, 1967
Cited by (2)

22
 On the problems of sample size in pattern recognition

RAUDYS S.
Proc., 2nd AllUnion Conf. Statistical Methods in Control Theory 2, 6467, 1970
Cited by (1)

23
 On the amount of a priori information in designing the classification algorithm

RAUDYS S.
Proc. Acad. of Sci. of USSR Technical. Cybernetics 4, 168174, 1972
Cited by (1)

24
 On shape of pattern error function, initializations and intrinsic dimensionality in ANN classifier design

RAUDYS S.
Informatica, Vilnius 4(34), 360383, 1993
Cited by (1)

25
 Expected error of minimum empirical error and maximal margin classifiers

RAUDYS S.
Proceedings 13th ICPR 2, 875879, 1996
Cited by (1)

26
 Small sample properties of ridge estimate of the covariance matrix in tratistical and neural net classfication

RAUDYS S.
New Trends in Probability and Statistics, Multivariate Statistics and Matrices in Statistics, Proc. of the 5th Tartu Conference 3, 237245, 1994
Cited by (1)

27
 Learning internal representations by error propagation

RUMELHART D. E.
Parallel distributed processing : Explorations in the microstucture of cognition 1, 318362, 1986
Cited by (1)

28
 Overtraining, regularization, and searching for minimum in neural networks

SJOBERG J.
Technical report, 1992
Cited by (1)

29
 Some results on the distribution of the Wclassifications statistics

SIGREAVES R.
Studies in Item Selection and Prediction, 241261, 1961
Cited by (1)

30
 Probability and statistics in psychometric research

SOLOMON H.
Proc. of 3rd Berkley Symposium on Mathematical statistics and Probability, 169184, 1956
Cited by (1)

31
 Optimal local Hebbian learning : use the drule

VAN DAM J. W. M.
Artificial Neural Networks, Proc. ICANN'94, 631634, 1994
Cited by (1)

32
 Algorithms with full memory and recurrence algorithms in the problem of training pattern recognition

VAPNIK V. N.
Engineering Cybernetics (USSR J. ) N4, 95106, 1968
Cited by (1)

33
 Adaptive switching circuits

WIDROW B.
WESCON Convention Record 4, 96104, 1960
Cited by (1)

34
 The mathematics of generalization

WOLPERT D. H. (Ed.)
Proceedings of the SFI/CNLS workshop on formal approach to supervised learning, 1995
Cited by (1)

35
 On relation between PAC, the statistical physics framework, the Bayesian framework, and the VC framework

WOLPERT D. H.
Proceedings of the SFI/CNLS workshop on formal approach to supervised learning, 1995
Cited by (1)

36
 The use of models of simple dependence problems of classification

ZARUDSKIJ V. I.
Statistical Problems of Control, Issue 38, 3375, 1979
Cited by (1)

37
 A theory of adaptive pattern classifiers

AMARI S.
IEEE Trans. Electron. Comput. EC16, 299307, 1967
DOI Cited by (48)

38
 A universal theorem on learning curves

AMARI S.
Neural Networks 6(2), 161166, 1993
Cited by (24)

39
 Four types of learning curves.

AMARI S.
Neural Computation 4(4), 608618, 1992
DOI Cited by (19)

40
 Statistical theory of learning curves under entropic loss

AMARI S. I.
Neural Computation 5, 140153, 1993
DOI Cited by (25)

41
 Scaling Laws in Learning of Classification Tasks

BARKAI N.
Physical Review Letters, 1993
Cited by (2)

42
 The prediction error of stationary Gaussian time series of unknown covariance

DEVISSON L. O.
IEEE Transactions on Information Theory IT11, 527532, 1965
DOI Cited by (2)

43
 Stochastic linear learning: Exact test and training error averages

HANSEN L. K.
Neural Networks 6, 393396, 1993
Cited by (3)

44
 On the mean accuracy of statistical pattern recognizers

HUGHES G. F.
IEEE Trans. Info. Theory IT14(1), 5563, 1968
DOI Cited by (15)

45
 Dimensionality and Sample Size Considerations in Pattern Recognition Practice

JAIN A.
Handbook of Statistics 2, 835855, 1982
DOI Cited by (8)

46
 Errors in discrimination

JOHN S.
Ann. Math. Statistics 32, 11251144, 1961
DOI Cited by (1)

47
 Model of generalization error in learning systems with training error selection

KOWALCZYK A.
Progress in neural information processing, Proc. ICONIP'96, 180187, 1996
Cited by (1)

48
 Empirical risk minimization versus maximumlikelihood estimation : a case study

MEIR R.
Neural Computation 1, 144157, 1995
Cited by (1)

49
 Errors in classifying multivariate observations

MESHALKIN L. D.
Theory of Probabilities and Applications 23(4), 772781, 1978
DOI Cited by (1)

50
 An asymptotic expansion for the distribution of the linear discriminant function

OKAMOTO M.
Ann. Math. Statist. 34, 12861301, 1963
DOI Cited by (5)

51
 An asymptotic expansion for the distribution of the linear discriminant function

OKAMOTO M.
Ann. Math. Statist. 39, 13581359, 1968
DOI Cited by (2)

52
 Evolution and generalization of a single nourone : I. Singlelayer perceptron as seven statistical classifiers

RAUDYS Sarunas
Neural Networks 11(2), 283296, 19980301
References (38) Cited by (5)

53
 Small sample size effects in statistical pattern recognition : Recommendations for practitioners

RAUDYS S. J.
IEEE Trans. Pattern Analysis & Machine Intelligence 13(3), 252264, 1991
Cited by (18)

54
 On dimensionality, sample size, classification error, and complexity of classification algorithm in pattern recognition

RAUDYS S.
IEEE Trans. PAMI2, 3, 242252, 1980
Cited by (4)

55
 Statisticalmechanics of learning from examples

SEUNG H. S.
Phy. Rev. A, 1992
Cited by (10)

56
 Experimental study of performance of pattern classifiers and the size of design samples

TAKESHITA T.
Pattern Recognition letters 16(3), 307312, 1995
Cited by (7)

57
 A theory of the learnable

L. G. Valiant
Communications of ACM 27, 11341142, 1984
DOI Cited by (101)

58
 A comparison of asymptotic error rate expansions for the sample linear discriminant function

WYMAN F.
Pattern Recognition 23, 775783, 1990
Cited by (2)
Cited by: 2

1
 Evolution and generalization of a single neurone. III. Primitive, regularized, standard, robust and minimax regressions

RAUDYS S.
Neural networks : the official journal of the International Neural Network Society 13(4), 507523, 20000501
References (27)

2
 Trainable fusion rules : II. Small samplesize effects

RAUDYS Sarunas
Neural networks : the official journal of the International Neural Network Society 19(10), 15171527, 20061201
References (24)