메뉴 건너뛰기




Volumn 4, Issue 3-4, 1993, Pages 360-383

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

Author keywords

Feed forward neural nets; Generalization; Initialization; Insufficient learning; Intrinsic dimensionality; Training sample size

Indexed keywords


EID: 84974762231     PISSN: 08684952     EISSN: None     Source Type: Journal    
DOI: 10.3233/INF-1993-43-410     Document Type: Article
Times cited : (11)

References (18)
  • 1
    • 0041304168 scopus 로고
    • When k-nearest neighbor and back propagation accurate for feasible sized sets of examples
    • L.B. Almeida and C.J. Wellekens (Eds.), Pattern Recognition Group, Department of Applied Physics, Delft University of Technology, Delft
    • Baum, E.B. (1990). When k-nearest neighbor and back propagation accurate for feasible sized sets of examples. In L.B. Almeida and C.J. Wellekens (Eds.), Proceedings of the EURASP Workshop on Neural Networks, Pattern Recognition Group, Department of Applied Physics, Delft University of Technology, Delft.
    • (1990) Proceedings of the EURASP Workshop on Neural Networks
    • Baum, E.B.1
  • 2
    • 0039596307 scopus 로고
    • Representation of statistics of discriminant analysis and asymptotic expansions in dimensionalities comparable with sample size
    • (in Russian)
    • Deev, A.D. (1970). Representation of statistics of discriminant analysis and asymptotic expansions in dimensionalities comparable with sample size. Reports of Academy of Sciences of the USSR, 195(4), 756-762 (in Russian).
    • (1970) Reports of Academy of Sciences of the USSR , vol.195 , Issue.4 , pp. 756-762
    • Deev, A.D.1
  • 3
    • 0008819287 scopus 로고
    • Superlearning capabilities of neural networks
    • NOVIM, Norwegian Society for Image Processing and Pattern Recognition, Tromso, Norway
    • Duin, R.P.W. (1993). Superlearning capabilities of neural networks. In Proc. of the 8th Scandinavian Conference on Image Analysis, NOVIM, Norwegian Society for Image Processing and Pattern Recognition, Tromso, Norway, pp. 547-554.
    • (1993) Proc. of the 8Th Scandinavian Conference on Image Analysis , pp. 547-554
    • Duin, R.P.W.1
  • 4
    • 84974774547 scopus 로고
    • On training sample size and complexity of artificial neural net classifier
    • Jain, A., and Š. Raudys (1992). On training sample size and complexity of artificial neural net classifier. Information, 3(2), 301-337.
    • (1992) Information , vol.3 , Issue.2 , pp. 301-337
    • Jain, A.1    Raudys, Š.2
  • 5
    • 0041698202 scopus 로고
    • The use of an adaptive threshold element to design a linear optimal pattern classifier
    • Koford, J.S., and G.F. Groner (1966). The use of an adaptive threshold element to design a linear optimal pattern classifier. IEEE Trans. Inf. Theory, IT-12, 42-50.
    • (1966) IEEE Trans. Inf. Theory , vol.IT-12 , pp. 42-50
    • Koford, J.S.1    Groner, G.F.2
  • 8
    • 0344422338 scopus 로고
    • Comparison of methods of computing the expected classification errors
    • (in Russian)
    • Pikelis, V. (1976). Comparison of methods of computing the expected classification errors. Automation and Remote Control, 5, 59-63 (in Russian).
    • (1976) Automation and Remote Control , vol.5 , pp. 59-63
    • Pikelis, V.1
  • 9
    • 0026120032 scopus 로고
    • Small sample size effects in statistical pattern recognition: Recommendations for practitioners
    • Raudys, Š., and A.K. Jain (1991). Small sample size effects in statistical pattern recognition: Recommendations for practitioners. IEEE Trans, on PatternAnalysis and Machine Intelligence, 13, 252-264.
    • (1991) IEEE Trans, on PatternAnalysis and Machine Intelligence , vol.13 , pp. 252-264
    • Raudys, Š.1    Jain, A.K.2
  • 10
    • 84974761680 scopus 로고
    • Small sample problems in designing artificial neural, networks
    • I.K. Sethi and A.K. Jain (Eds.)
    • Raudys, Š., and A. Jain (1991a). Small sample problems in designing artificial neural, networks. In I.K. Sethi and A.K. Jain (Eds.), Elsevier Sci. Publ.NY, pp. 33-50.
    • (1991) Elsevier Sci. Publ.NY , pp. 33-50
    • Raudys, Š.1    Jain, A.2
  • 11
    • 0019020917 scopus 로고
    • On dimensionality, sample size, classification error and complexity of classification algorithm in pattern recognition
    • Raudys, Š., and V. Pikelis (1980). On dimensionality, sample size, classification error and complexity of classification algorithm in pattern recognition. IEEETrans, on PA MI, PAMI-2(3), 242-252.
    • (1980) IEEETrans, on PA MI , vol.PAMI-2 , Issue.3 , pp. 242-252
    • Raudys, Š.1    Pikelis, V.2
  • 12
    • 84974765217 scopus 로고
    • On the effectiveness of Parzen window classifier
    • Raudys, Š. (1991). On the effectiveness of Parzen window classifier. Information, 2(3), 434-454.
    • (1991) Information , vol.2 , Issue.3 , pp. 434-454
    • Raudys, Š.1
  • 13
    • 0007826528 scopus 로고
    • On amount at a prior information in designing the classification algorithm
    • Raudys, Š. (1992). On amount at a prior information in designing the classification algorithm. Proc. Acad, of Sciences of the USSR. Tech. Cyber., 4, 168-174.
    • (1992) Proc. Acad, of Sciences of the USSR. Tech. Cyber. , vol.4 , pp. 168-174
    • Raudys, Š.1
  • 14
    • 0000646059 scopus 로고
    • Learning internal representations by error propagation
    • D.E. Rumelhart and J.L. KcClelland (Eds.), MA:MIT Pres, Cambridge
    • Rumelhart, D.E., G.E. Hinton and R.J. Williams (1986). Learning internal representations by error propagation. In D.E. Rumelhart and J.L. KcClelland (Eds.), Parallel Distributed Processing, MA:MIT Pres, Cambridge.
    • (1986) Parallel Distributed Processing
    • Rumelhart, D.E.1    Hinton, G.E.2    Williams, R.J.3
  • 17
    • 0025659671 scopus 로고
    • A comparison of asymptotic error rate expansions for the sample linear discriminant function
    • Wyman, F., D. Young and D. Turner (1990). A comparison of asymptotic error rate expansions for the sample linear discriminant function. Pattern Recognition, 23, 775-783.
    • (1990) Pattern Recognition , vol.23 , pp. 775-783
    • Wyman, F.1    Young, D.2    Turner, D.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.