메뉴 건너뛰기




Volumn 21, Issue 4, 2005, Pages 721-732

Geometrical perspective on learning behavior

Author keywords

Back propagation learning; Momentum method; Multilayer network; Neural network; Premature saturation

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; BACKPROPAGATION; BEHAVIORAL RESEARCH; COMPUTATIONAL GEOMETRY; DECISION THEORY; METHOD OF MOMENTS; PERSONNEL TRAINING;

EID: 22144480950     PISSN: 10162364     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article
Times cited : (3)

References (9)
  • 1
    • 84918441630 scopus 로고
    • Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition
    • T. M. Cover, "Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition," IEEE Transitions on Electronic Computers, Vol. 14, 1965, pp. 326-334.
    • (1965) IEEE Transitions on Electronic Computers , vol.14 , pp. 326-334
    • Cover, T.M.1
  • 2
    • 0024137490 scopus 로고
    • Increased rates of convergences through learning rate adaptation
    • R. A. Jacobs, "Increased rates of convergences through learning rate adaptation," Neural Networks, Vol. 1, 1988, pp. 295-307.
    • (1988) Neural Networks , vol.1 , pp. 295-307
    • Jacobs, R.A.1
  • 3
    • 0027226690 scopus 로고
    • An analysis of premature saturation in back propagation learning
    • Y. Lee, S. H. Oh, and M. W. Kim, "An analysis of premature saturation in back propagation learning," Neural Network, Vol. 6, 1993, pp. 719-728.
    • (1993) Neural Network , vol.6 , pp. 719-728
    • Lee, Y.1    Oh, S.H.2    Kim, M.W.3
  • 4
    • 0024765401 scopus 로고
    • Analysis and synthesis of a class of neural networks: Linear systems operating on a closed hypercube
    • J. Li, A. N. Michel, and W. Porod, "Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercube," IEEE Transactions on Circuits and Systems, Vol. 36, 1989, pp. 1405-1422.
    • (1989) IEEE Transactions on Circuits and Systems , vol.36 , pp. 1405-1422
    • Li, J.1    Michel, A.N.2    Porod, W.3
  • 6
    • 0022471098 scopus 로고
    • Learning representations by back-propagating errors
    • D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," Nature, Vol. 323, 1986, pp. 533-536.
    • (1986) Nature , vol.323 , pp. 533-536
    • Rumelhart, D.E.1    Hinton, G.E.2    Williams, R.J.3
  • 7
    • 84882420668 scopus 로고
    • Acceleration technique for the backpropagation algorithm
    • L. B. Almeida and C. J. Wellekens (eds.)
    • F. M. Silva and L. B. Almeida, "Acceleration technique for the backpropagation algorithm," in Proceedings of Neural Networks EURASIP Workshop, L. B. Almeida and C. J. Wellekens (eds.), 1990, pp. 110-119.
    • (1990) Proceedings of Neural Networks EURASIP Workshop , pp. 110-119
    • Silva, F.M.1    Almeida, L.B.2
  • 8
    • 0023541050 scopus 로고
    • Learning algorithms for connectionist networks: Applied gradient methods of nonlinear optimization
    • R. L. Watrous, "Learning algorithms for connectionist networks: applied gradient methods of nonlinear optimization," in FIRST IEEE International Conference on Neural Networks, Vol. 2, 1987, pp. 619-627.
    • (1987) FIRST IEEE International Conference on Neural Networks , vol.2 , pp. 619-627
    • Watrous, R.L.1
  • 9
    • 0025503558 scopus 로고
    • Backpropagation through time: What it does and how to do it
    • P. J. Werbos, "Backpropagation through time: what it does and how to do it," in Proceedings of the IEEE, Vol. 78, 1990, pp. 1550-1560.
    • (1990) Proceedings of the IEEE , vol.78 , pp. 1550-1560
    • Werbos, P.J.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.