메뉴 건너뛰기




Volumn 10, Issue 2, 1997, Pages 299-314

Dynamical neural networks that ensure exponential identification error convergence

Author keywords

dynamical system identification; recurrent high order neural networks; robust adaptive algorithms

Indexed keywords

ADAPTIVE ALGORITHMS; ERRORS; IDENTIFICATION (CONTROL SYSTEMS); LEARNING SYSTEMS; MATHEMATICAL MODELS;

EID: 0031106016     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(96)00060-3     Document Type: Article
Times cited : (100)

References (25)
  • 2
    • 0020970741 scopus 로고
    • Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
    • Cohen, M. A., & Grossberg, S. (1983). Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Transactions on Systems, Man and Cybernetics, SMC-13, 815-826.
    • (1983) IEEE Transactions on Systems, Man and Cybernetics , vol.SMC-13 , pp. 815-826
    • Cohen, M.A.1    Grossberg, S.2
  • 4
    • 0024861871 scopus 로고
    • Approximations by superpositions of a sigmoidal function
    • Cybenko, G. (1989). Approximations by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems, 2, 303-314.
    • (1989) Mathematics of Control, Signals, and Systems , vol.2 , pp. 303-314
    • Cybenko, G.1
  • 6
    • 0024866495 scopus 로고
    • On the approximate realization of continuous mappings by neural networks
    • Funahashi, K. (1989). On the approximate realization of continuous mappings by neural networks. Neural Networks, 2, 183-192.
    • (1989) Neural Networks , vol.2 , pp. 183-192
    • Funahashi, K.1
  • 8
    • 0004469897 scopus 로고
    • Neurons with graded response have collective computational properties like those of two-state neurons
    • Hopfield, J. J. (1984). Neurons with graded response have collective computational properties like those of two-state neurons. Procedings National Academy of Sciences, 81, 3088-3092.
    • (1984) Procedings National Academy of Sciences , vol.81 , pp. 3088-3092
    • Hopfield, J.J.1
  • 14
    • 0025399567 scopus 로고
    • Identification and control of dynamical systems using neural networks
    • Narendra, K. S., & Parthasarathy, K. (1990). Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks, 1(1), 4-27.
    • (1990) IEEE Transactions on Neural Networks , vol.1 , Issue.1 , pp. 4-27
    • Narendra, K.S.1    Parthasarathy, K.2
  • 15
    • 0026117466 scopus 로고
    • Gradient methods for the optimization of dynamical systems containing neural networks
    • Narendra, K. S., & Parthasarathy, K. (1991). Gradient methods for the optimization of dynamical systems containing neural networks. IEEE Transactions on Neural Networks, 2(1), 252-262.
    • (1991) IEEE Transactions on Neural Networks , vol.2 , Issue.1 , pp. 252-262
    • Narendra, K.S.1    Parthasarathy, K.2
  • 17
    • 0000442791 scopus 로고
    • Generalization of back propagation to recurrent networks
    • Pinenda, F. J. (1988). Generalization of back propagation to recurrent networks. Physics Review Letters, 59(19), 2229-2232.
    • (1988) Physics Review Letters , vol.59 , Issue.19 , pp. 2229-2232
    • Pinenda, F.J.1
  • 19
    • 0000646059 scopus 로고
    • Learning internal representations by error propagation
    • D. Rumelhart & F. McClelland, (Eds), Cambridge, MA: MIT Press
    • Rumelhart, D., Hinton, D., & Williams, G. (1986). Learning internal representations by error propagation. In D. Rumelhart & F. McClelland, (Eds), Parallel distributed processing, (Volume 2), Cambridge, MA: MIT Press.
    • (1986) Parallel Distributed Processing , vol.2
    • Rumelhart, D.1    Hinton, D.2    Williams, G.3
  • 24
    • 0025503558 scopus 로고
    • Backpropagation through time: What it does and how to do it
    • Werbos, P. J. (1990). Backpropagation through time: what it does and how to do it. Proceedings IEEE, 78, 1550-1560.
    • (1990) Proceedings IEEE , vol.78 , pp. 1550-1560
    • Werbos, P.J.1
  • 25
    • 0001202594 scopus 로고
    • A learning algorithm for continually running fully recurrent neural networks
    • Williams, R. J., & Zipser, D. (1989). A learning algorithm for continually running fully recurrent neural networks. Neural Computation, 1, 270-280.
    • (1989) Neural Computation , vol.1 , pp. 270-280
    • Williams, R.J.1    Zipser, D.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.