메뉴 건너뛰기




Volumn 3, Issue 1, 2003, Pages 115-143

Learning precise timing with LSTM recurrent networks

Author keywords

Long Short Term Memory; Recurrent Neural Networks; Timing

Indexed keywords

MARKOV PROCESSES; RECURRENT NEURAL NETWORKS; SPEECH RECOGNITION; VIRTUAL REALITY;

EID: 0041965934     PISSN: 15324435     EISSN: None     Source Type: Journal    
DOI: 10.1162/153244303768966139     Document Type: Article
Times cited : (1542)

References (24)
  • 2
    • 0028392483 scopus 로고
    • Learning long-term dependencies with gradient descent is difficult
    • Y. Bengio, P. Simard, and P. Frasconi. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2):157-166, 1994.
    • (1994) IEEE Transactions on Neural Networks , vol.5 , Issue.2 , pp. 157-166
    • Bengio, Y.1    Simard, P.2    Frasconi, P.3
  • 3
    • 0028965995 scopus 로고
    • A recurrent network for modelling noisy temporal sequences
    • A.B. Bulsari and H. Saxén. A recurrent network for modelling noisy temporal sequences. Neuro-computing, 7:29-40, 1995.
    • (1995) Neuro-computing , vol.7 , pp. 29-40
    • Bulsari, A.B.1    Saxén, H.2
  • 4
    • 0039222571 scopus 로고    scopus 로고
    • Language identification from prosody without explicit features
    • Fred Cummins, Felix Gers, and Jürgen Schmidhuber. Language identification from prosody without explicit features. In Proceedings of EUROSPEECH'99, volume 1, pages 371-374, 1999.
    • (1999) Proceedings of EUROSPEECH'99 , vol.1 , pp. 371-374
    • Cummins, F.1    Gers, F.2    Schmidhuber, J.3
  • 5
    • 0024875962 scopus 로고
    • Adaptive neural oscillator using continuous-time backpropagation learning
    • K. Doya and S. Yoshizawa. Adaptive neural oscillator using continuous-time backpropagation learning. Neural Networks, 2(5):375-385, 1989.
    • (1989) Neural Networks , vol.2 , Issue.5 , pp. 375-385
    • Doya, K.1    Yoshizawa, S.2
  • 6
    • 84902197186 scopus 로고    scopus 로고
    • Learning the long-term structure of the blues
    • Lecture Notes in Computer Science. Springer Verlag, Berlin (in press)
    • D. Eck and J. Schmidhuber. Learning the long-term structure of the blues. In Proc. Intl. Conf. Artificial Neural Networks, Lecture Notes in Computer Science. Springer Verlag, Berlin (in press), 2002.
    • (2002) Proc. Intl. Conf. Artificial Neural Networks
    • Eck, D.1    Schmidhuber, J.2
  • 7
    • 0003979694 scopus 로고
    • Learning the initial state of a second-order recurrent neural network during regular-language inference
    • Mikel L. Forcada and Rafael C. Carrasco. Learning the initial state of a second-order recurrent neural network during regular-language inference. Neural Computation, 7(5):923-930, 1995.
    • (1995) Neural Computation , vol.7 , Issue.5 , pp. 923-930
    • Forcada, M.L.1    Carrasco, R.C.2
  • 8
    • 0035505385 scopus 로고    scopus 로고
    • LSTM recurrent networks learn simple context free and context sensitive languages
    • F. A. Gers and J. Schmidhuber. LSTM recurrent networks learn simple context free and context sensitive languages. IEEE Transactions on Neural Networks, 2001.
    • (2001) IEEE Transactions on Neural Networks
    • Gers, F.A.1    Schmidhuber, J.2
  • 9
    • 0034293152 scopus 로고    scopus 로고
    • Learning to forget: Continual prediction with LSTM
    • F. A. Gers, J. Schmidhuber, and F. Cummins. Learning to forget: Continual prediction with LSTM. Neural Computation, 12(10):2451-2471, 2000.
    • (2000) Neural Computation , vol.12 , Issue.10 , pp. 2451-2471
    • Gers, F.A.1    Schmidhuber, J.2    Cummins, F.3
  • 10
    • 0003575034 scopus 로고
    • Diploma thesis, Institut für Informatik, Lehrstuhl Prof. Brauer, Technische Universität München
    • S. Hochreiter. Untersuchungen zu dynamischen neuronalen Netzen. Diploma thesis, Institut für Informatik, Lehrstuhl Prof. Brauer, Technische Universität München, 1991. See www7.informatik.tu-muenchen.de/̃hochreit.
    • (1991) Untersuchungen zu Dynamischen Neuronalen Netzen
    • Hochreiter, S.1
  • 11
  • 13
    • 0001857994 scopus 로고    scopus 로고
    • Efficient backprop
    • Genevieve B. Orr and Klaus-Robert Müller, editors, Neural Networks - Tricks of the Trade. Springer Verlag, Berlin
    • Y. LeCun, L. Bottou, G.B. Orr, and K.-R. Müller. Efficient backprop. In Genevieve B. Orr and Klaus-Robert Müller, editors, Neural Networks - Tricks of the Trade, volume 1524 of Lecture Notes in Computer Science, pages 5-50. Springer Verlag, Berlin, 1998.
    • (1998) Lecture Notes in Computer Science , vol.1524 , pp. 5-50
    • LeCun, Y.1    Bottou, L.2    Orr, G.B.3    Müller, K.-R.4
  • 14
    • 0029375851 scopus 로고
    • Gradient calculations for dynamic recurrent neural networks: A survey
    • B. A. Pearlmutter. Gradient calculations for dynamic recurrent neural networks: A survey. IEEE Transactions on Neural Networks, 6(5):1212-1228, 1995.
    • (1995) IEEE Transactions on Neural Networks , vol.6 , Issue.5 , pp. 1212-1228
    • Pearlmutter, B.A.1
  • 15
    • 0003794792 scopus 로고
    • Experiments on learning back propagation
    • Carnegie-Mellon University, Pittsburgh, PA
    • D. C. Plaut, S. J. Nowlan, and G. E. Hinton. Experiments on learning back propagation. Technical Report CMU-CS-86-126, Carnegie-Mellon University, Pittsburgh, PA, 1986.
    • (1986) Technical Report , vol.CMU-CS-86-126
    • Plaut, D.C.1    Nowlan, S.J.2    Hinton, G.E.3
  • 16
    • 0003838146 scopus 로고
    • The utility driven dynamic error propagation network
    • Cambridge University Engineering Department
    • A. J. Robinson and F. Fallside. The utility driven dynamic error propagation network. Technical Report CUED/F-INFENG/TR.1, Cambridge University Engineering Department, 1987.
    • (1987) Technical Report , vol.CUED-F-INFENG-TR.1
    • Robinson, A.J.1    Fallside, F.2
  • 17
    • 0000053463 scopus 로고
    • 3) time complexity learning algorithm for fully recurrent continually running networks
    • 3) time complexity learning algorithm for fully recurrent continually running networks. Neural Computation, 4(2):243-248, 1992.
    • (1992) Neural Computation , vol.4 , Issue.2 , pp. 243-248
    • Schmidhuber, J.1
  • 19
    • 0041413341 scopus 로고    scopus 로고
    • Existence and learning of oscillations in recurrent neural networks
    • Universitaet Kaiserslautern, Fachbereich Mathematik, Kaiserslautern, Germany
    • S. Townley, A. Ilchmann, M. G. Weiss, W. McClements, A. C. Ruiz, D. Owens, and D. Praetzel-Wolters. Existence and learning of oscillations in recurrent neural networks. Technical Report AGTM 202, Universitaet Kaiserslautern, Fachbereich Mathematik, Kaiserslautern, Germany, 1999.
    • (1999) Technical Report , vol.AGTM 202
    • Townley, S.1    Ilchmann, A.2    Weiss, M.G.3    McClements, W.4    Ruiz, A.C.5    Owens, D.6    Praetzel-Wolters, D.7
  • 21
    • 0042916539 scopus 로고    scopus 로고
    • Learning oscillations using adaptive control
    • Universitaet Kaiserslautern, Fachbereich Mathematik, Kaiserslautern, Germany
    • M. G. Weiss. Learning oscillations using adaptive control. Technical Report AGTM 178, Universitaet Kaiserslautern, Fachbereich Mathematik, Kaiserslautern, Germany, 1999.
    • (1999) Technical Report , vol.AGTM 178
    • Weiss, M.G.1
  • 22
    • 0001609567 scopus 로고
    • An efficient gradient-based algorithm for on-line training of recurrent network trajectories
    • R. J. Williams and J. Peng. An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural Computation, 2(4):490-501, 1990.
    • (1990) Neural Computation , vol.2 , Issue.4 , pp. 490-501
    • Williams, R.J.1    Peng, J.2
  • 23
    • 0001202594 scopus 로고
    • A learning algorithm for continually running fully recurrent net works
    • R. J. Williams and D. Zipser. A learning algorithm for continually running fully recurrent net works. Neural Computation, 1(2):270-280, 1989.
    • (1989) Neural Computation , vol.1 , Issue.2 , pp. 270-280
    • Williams, R.J.1    Zipser, D.2
  • 24
    • 0001765578 scopus 로고
    • Gradient-based learning algorithms for recurrent networks and their computational complexity
    • Y. Chauvin and D. E. Rumelhart, editors, chapter 13. Hillsdale, NJ: Erlbaum
    • R. J. Williams and D. Zipser. Gradient-based learning algorithms for recurrent networks and their computational complexity. In Y. Chauvin and D. E. Rumelhart, editors, Back-propagation: Theory, Architectures and Applications, chapter 13, pages 433-486. Hillsdale, NJ: Erlbaum, 1992.
    • (1992) Back-propagation: Theory, Architectures and Applications , pp. 433-486
    • Williams, R.J.1    Zipser, D.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.