文献目録

1

C.M.Bishop, Neural Networks for Pattern Recognition, Oxford Univ. Press, 1995.

2

B.D.Ripley, Pattern Recognition and Neural Networks, Cambridge Univ. Press, 1996.

3

C.K.Chow, ``An optimum character recognition system using decision functions,'' IRE Trans., Vol.EC-6, pp.247-254, 1957.

4

麻生(1988):``ニューラルネットワーク情報処理,'' 産業図 書, .

5

Minsky,M. and Papert,S.(1969): ``Perceptrons,'' MIT Press, .

6

Rumelhart,D.E.,Hinton, G.E. and Williams,R.J.(1986): ``Learning representaions by back-propagating errors,'' Nature, Vol.323-9, pp.533-536.

7

Rumelhart,D.E., Hinton,G.E., and Williams,R.J.,(1986): ``Learning internal represenations by error propagation,'' in Parallel Distributed Processing Volume 1, J.L.McCleland, D.E.Rumelhard, and The PDP Ressearch group, MIT Press.

8

Hopfield,J.J.,(1982): ``Neural networks and phisical systems with emargent collective computational abilities,'' Proc. of the National Academy of Sciences USA 79, pp.2254-2258.

9

Hopfield,J.J.(1984): ``Neurons with graded responce have collective computational properties like those of two-state neurons,'' Proc. of the National Academy of Sciences USA 81, pp.3088-3092.

10

Farlman,S.E.,Hinton,G.E., and Sejnowski,T.J.,(1983): ``Massively parallel architectures for AI: NETL, Thistle, and Boltzman Machines,'' Proc. of the National Conf. on Artificial Intelligence AAAI-83, pp.109-113.

11

Hinton,G.E., Sejnowski,T.J. and Ackley,D.H.,(1984): ``Boltzmann Machines : Constraint satisfaction networks that learn,'' Tech. Rep. CMU-CS-84-119.

12

Hinton,G.E. and Sejnowski,T.J.,(1986): ``Learning and relearning in Boltzmann Machines,'' in Parallel Distributed Preocessing Volume 1, J.L.McCleland, D.E.Rumelhard, and The PDP Ressearch group, MIT Press.

13

Hush,D.R. and Horne,B.G.,(1993): ``Progress in supervised neural networks,'' IEEE Signal Processing Magazine, pp.8-39.

14

Otsu,N.(1982): ``Optimal linear and nonlinear solutions for least-square discriminant feature extraction,'' Proc. 6th ICPR, pp.557-560.

15

Otsu,N. Kurita,T. and Asoh,H.(1988): ``A unified study of multivariate analysis methods by nonlinear extensions and underlying probabilistic structures,'' in Recent Developments of Clustering and Data Analysis, E.Diday et al. eds., Academic Press.

16

Cybenko,G.,(1989): ``Approximation by superpositions of a sigmoidal function,'' Mathematics of Control, Signals, and Systems, Vol.2, No.4, pp.303-314.

17

栗田,(1991): ``階層型ニューラルネットのパラメータの 最尤推定について,'' 電子情報通信学会, ニューラルコンピューティング研究 会資料, NC91-36.

18

Kurita,T.(1992): ``Iterative weighted least squares algorithms for neural networks classifiers,'' Proc. of the Third Workshop on Algorithmic Learning Theory, Tokyo, Oct. 20-22.

19

Baum,E.B. and Haussle,D.,(1989): ``What size net gives valid generalization ?,'' Neural Computation, Vol.1, pp.151-160.

20

Akaho,S.,(1992): ``Regularization learning of neural networks for generalization,'' Proc. of the Third Workshop on Algorithmic Learning Theory, Tokyo, Oct. 20-22.

21

Hanson,S.J. and Pratt,L.Y.,(1989): `` Comparing biases for minimal network construction with back-propagation,'' In D.S.Touretzky, ed. Advances in Neural Information Processing Systems 1, pp.177-185, Morgan kaufmann.

22

Sekita,I., Kurita,T., Asoh,H., and Chiu,D.(1993): ``Reconfigurating feedforward networks with fewer hidden nodes,'' Proc. of SPIE conf. on Adaptive and Learning Systems II. (to be appear).

23

Miller,R.G.,(1974): ``The jacknife -a review,'' Biometrika, Vol.61, No.1, pp.1-15.

24

Stone,M.,(1974): ``Cross-validatory choice and assessment of statistic al predictions,'' Journal of Royal Statistical Society, Vol.B36, pp.111-147.

25

Efron,B.,(1979): ``Bootstrap methods: anothoe look at the jackknife,'' The Annals of Statistics, Vol.7, No.1, pp.1-26.

26

Efron,B.,(1983): ``Estimating the error rate of a prediction rule: imp rovements in cross-validation,'' Journal of Amerian Statistical Association, Vol .78, pp.316-331.

27

Efron,B.,(1985): ``The bootstrap method for assessing statistical accu racy,'' Behaviormetrika, Vol.17, pp.1-35.

28

Akaike,H.,(1974): ``A new look at the statistical model identification,'' IEEE Trans. on Automatic Control, vol.AC-19, No.6, pp.716-723.

29

坂本, 石黒, 北川,(1983): ``情報量統計学,'' 共立出 版.

30

Rissanen,J.,(1983): ``A universal prior for integers and estimation by minimum description length,'' The Annals of Statistics, Vol.11, NO.2, pp.416-431.

31

Rissanen,J.,(1986): ``Stochastic complexity and modeling,'' The Annals of Statistics, Vol.14, No.3, pp.1080-1100.

32

栗田,(1990): ``情報量基準による３層ニューラルネット の隠れ層のユニット数の決定法,'' 電子情報通信学会論文誌, Vol.J73-D-II, No.11, pp.1872-1878.

33

Possio,T. and Girosi,F.,(1990): ``Networks for approximation and learning,'' Proc. of the IEEE, Vol.78, No.9, pp.1481-1497.

34

Fahlman,S.E.,(1988): ``An empirical study of learning speed in back-propagation networks,'' Tech. Report, CMU-CS-88-162.

35

Fahlman,S.E. and Lebiere,C.,(1990): ``The cascade-correlation learning architecture,'' in D.Touretzky, editor, Advances in Neural Information Precessing Systems 2, pp.524-532, Morgan Kaufmann.

36

Ivakhnenko,A.C.,(1971): ``Polynomial theory of complex systems,'' IEEE Trans. on Systems, Man, and Cybernetics, Vol.SMC-1, No.4, pp.364-378.

37

Tenorio,M.F. and Lee,G.,(1990): ``Self-organizeing Network for optimum supervised learning,'' IEEE Trans. on Neural Networks, Vol.1, No.1.

38

Iba,H., Kurita,T., deGaris,H. and Sato,T.,(1993): ``System identification using structured genetic algorithms,'' Proc. of 5h Inter. Joint Conf. on Genetic Algorithms.

39

Cun,Y.L., Denker,J.S. and Solla,S.A.,(1990): ``Optimal brain damage,'' in D.Touretzky, editor, Advances in Neural Information Processing Systems 2, pp.598-605.

40

Hassibi,B. and Stork,D.G.,(1993): ``Second order derivatives for network pruning: Optimal brain surgeon,'' S.J.Handon, J.D.Cowan, and C.L.Giles, editers, Advances in Neural Information Processing Systems 5, Morgan Kaufman, pp.164-171.

41

Ishikawa,M.,(1989): ``A structural learning algorithm with forgetting of link weights,'' Porc. Inter. Joint. Conf. on Neural Networks.

42

石川,(1990): ``忘却を用いたコネクショニストモデル の構造学習アルゴリズム,'' 人工知能学会誌, Vol.5, No.5, pp.595-603.

43

Nowlan,S.J. and Hinton,G.E.,(1992): ``Simplifying neural networks by soft weight-sharing,'' Neural Computation, Vol.4, No.4, pp.473-493.

44

栗田, 麻生, 梅山, 赤穂, 細美, (1993):``独立なノイズ の付加による多層パーセプトロンの構造化学習,'' 電子情報通信学会技術報告, NC93-21, pp.71-77.

45

Murray,A.F. and Edwards,P.J.,(1993): ``Synaptic weight noise during multilayer perceptron training: falst tolerance and trainig improvements,'' IEEE Trans. on Neural Networks, Vol.4, NO.4, pp.722-725.

46

Asoh,H. and Otsu,N.,(1989): ``Nonlinear data analysis and multilayer perceptrons,'' Proc. of Inter. Joint Conf. on Neural Networks,'' Vol.II, pp.411-415.

47

Asoh,H. and Otsu,N.,(1990): ``An approximation of nonlinear discriminant analysis by multilayer neural networks,'' Proc. of Inter. Joint Conf. on Neural Network, Vol.III, pp.211-216.

48

Webb,A.R. and Lowe,D.,(1990): ``The optimised internal representaion of multilayer classifier networks performs nonlinear discriminant analysis,'' Neural Networks, Vol.3, pp.367-375.

49

Lowe,D. and Webb,A.R.,(1991): ``Optimized feature extraction and the Bayes decision in feed-forward classifier networks,'' IEEE Trans. on Pattern Analsysis and Machine Intelligence, VOl.PAMI-13, NO.4, pp.355-364.

50

Vapnik,V.,(1982):''Estimation of Dipendences Based on Empirical Data'' , Springer-Verlag.

51

Vapnik,V.,(1992):''Principles of Risk Minimization for Learning Theory'',Advanced in Neural Information Processing System 4,Morgan Kaufmann, pp.831-839.

52

Jordan,M.,Jacobs,R.,(1993): ''Hierarchical mixtures of experts and the EM algorithm,'' Proc. of IJCNN'93 NAGOYA.

53

Mackey,D.J.C.,(1992) ``A Practical Bayesian Framework for Backpropagation Networks,'' Neural Computation,4,pp.448-472.

54

甘利 他 ,(1993): ``ニューラルネットの新展開,'' サイエ ンス社.

55

麻生,(1992): ``期待損失最小化学習のための基準の比較,'' 電総研研究速報

56

Dempster,A., Laird,N. and Rubin,D., (1977): ``Maximum likelihood from incomple data via the EM algorithm,'' J. Roy. Statist. Soc. B, Vol.39, pp.1-38.

57

Amari,S., (1994): ``Information geometory of the EM and em algorithms for neural networks,'' Technical Report METR 94-04, University of Tokyo. (xxxxxx to appear in Neural Networks ****************)