메뉴 건너뛰기




Volumn 20, Issue 8, 2009, Pages 1267-1280

Segmented-memory recurrent neural networks

Author keywords

Gradient descent; Information latching; Long term dependencies; Recurrent neural networks (RNNs); Segmented memory; Vanishing gradient

Indexed keywords

GRADIENT DESCENT; INFORMATION LATCHING; LONG-TERM DEPENDENCIES; SEGMENTED MEMORY; VANISHING GRADIENT;

EID: 68949200806     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2009.2022980     Document Type: Article
Times cited : (23)

References (49)
  • 1
    • 0028392483 scopus 로고
    • Learning long-term dependencies with gradient descent is difficult
    • Mar
    • Y. Bengio, P. Simard, and P. Frasconi, "Learning long-term dependencies with gradient descent is difficult," IEEE Trans. Neural Netw., vol. 5, no. 2, pp. 157-166, Mar. 1994.
    • (1994) IEEE Trans. Neural Netw , vol.5 , Issue.2 , pp. 157-166
    • Bengio, Y.1    Simard, P.2    Frasconi, P.3
  • 2
    • 0036825531 scopus 로고    scopus 로고
    • Learning long-term dependencies by the selective addition of time-delayed connections to recurrent neural networks
    • R. Boné, M. Crucianu, and J. Beauville, "Learning long-term dependencies by the selective addition of time-delayed connections to recurrent neural networks," Neurocomputing, vol. 48, pp. 251-266, 2002.
    • (2002) Neurocomputing , vol.48 , pp. 251-266
    • Boné, R.1    Crucianu, M.2    Beauville, J.3
  • 3
    • 36248929319 scopus 로고    scopus 로고
    • Statistical analysis of long-range interactions in proteins
    • Las Vegas, NV, Jun
    • J. Chen and N. S. Chaudhari, "Statistical analysis of long-range interactions in proteins," in Proc. Int. Conf. Bioinf. Comput. Biol. Las Vegas, NV, Jun. 2006, pp. 296-302.
    • (2006) Proc. Int. Conf. Bioinf. Comput. Biol , pp. 296-302
    • Chen, J.1    Chaudhari, N.S.2
  • 4
    • 35048871535 scopus 로고    scopus 로고
    • Learning long-term dependencies in segmented memory recurrent neural networks
    • Advances in Neural Networks ISNN 2004, Berlin, Germany: Springer
    • J. M. Chen and N. S. Chaudhari, "Learning long-term dependencies in segmented memory recurrent neural networks," in Advances in Neural Networks ISNN 2004, ser. Lecture Notes in Computer Science. Berlin, Germany: Springer, 2004, vol. 3173, pp. 362-369.
    • (2004) ser. Lecture Notes in Computer Science , vol.3173 , pp. 362-369
    • Chen, J.M.1    Chaudhari, N.S.2
  • 5
    • 10044265071 scopus 로고    scopus 로고
    • Improvement of bidirectional recurrent neural network for learning long-term dependencies
    • Los Alamitos, CA, Aug
    • J. M. Chen and N. S. Chaudhari, "Improvement of bidirectional recurrent neural network for learning long-term dependencies," in Proc. 17th Int. Conf. Pattern Recognit., Los Alamitos, CA, Aug. 2004, vol. 4, pp. 593-596.
    • (2004) Proc. 17th Int. Conf. Pattern Recognit , vol.4 , pp. 593-596
    • Chen, J.M.1    Chaudhari, N.S.2
  • 6
    • 0042525850 scopus 로고    scopus 로고
    • An improved algorithm for learning long-term dependency problems in adaptive processing of data structures
    • Jul
    • S. Y. Cho, Z. Chi, W. C. Siu, and A. C. Tsoi, "An improved algorithm for learning long-term dependency problems in adaptive processing of data structures," IEEE Trans. Neural Netw., vol. 14, no. 4, pp. 781-793, Jul. 2003.
    • (2003) IEEE Trans. Neural Netw , vol.14 , Issue.4 , pp. 781-793
    • Cho, S.Y.1    Chi, Z.2    Siu, W.C.3    Tsoi, A.C.4
  • 7
    • 10944239548 scopus 로고    scopus 로고
    • Using latent attractors to discern temporal order
    • S. Doboli and A. A. Minai, "Using latent attractors to discern temporal order," in Proc. IEEE Int. Joint Conf. Neural Netw., 2004, vol. 2, pp. 1469-1474.
    • (2004) Proc. IEEE Int. Joint Conf. Neural Netw , vol.2 , pp. 1469-1474
    • Doboli, S.1    Minai, A.A.2
  • 8
    • 33750968805 scopus 로고    scopus 로고
    • Latent attractors: A general paradigm for context-dependent neural computation
    • K. Chen and L. Wang, Eds. New York: Springer-Verlag
    • S. Doboli and A. A. Minai, "Latent attractors: A general paradigm for context-dependent neural computation," in Trends in Neural Computation, K. Chen and L. Wang, Eds. New York: Springer-Verlag, 2007, vol. 35, pp. 135-169.
    • (2007) Trends in Neural Computation , vol.35 , pp. 135-169
    • Doboli, S.1    Minai, A.A.2
  • 9
    • 0001419757 scopus 로고
    • Distributed representations, simple recurrent networks, and grammatical structure
    • J. L. Elman, "Distributed representations, simple recurrent networks, and grammatical structure," Mach. Learn., vol. 7, no. 2/3, pp. 195-226, 1991.
    • (1991) Mach. Learn , vol.7 , Issue.2-3 , pp. 195-226
    • Elman, J.L.1
  • 10
    • 0030957127 scopus 로고    scopus 로고
    • The role of long-range interactions in defining the secondary structure of proteins is overestimated
    • A. Fiser, Z. Dosztanyi, and I. Simon, "The role of long-range interactions in defining the secondary structure of proteins is overestimated," Comput. Appl. Biosci., vol. 13, no. 3, pp. 297-301, 1997.
    • (1997) Comput. Appl. Biosci , vol.13 , Issue.3 , pp. 297-301
    • Fiser, A.1    Dosztanyi, Z.2    Simon, I.3
  • 11
    • 0003979694 scopus 로고
    • Learning the initial state of a second-order recurrent neural network during regular-language inference
    • M. L. Forcada and R. C. Carrasco, "Learning the initial state of a second-order recurrent neural network during regular-language inference," Neural Comput., vol. 7, pp. 923-930, 1995.
    • (1995) Neural Comput , vol.7 , pp. 923-930
    • Forcada, M.L.1    Carrasco, R.C.2
  • 12
    • 0024450126 scopus 로고
    • Explanations of grouping effects in immediate ordered recall
    • R. W. Frick, "Explanations of grouping effects in immediate ordered recall," Cognition, vol. 17, pp. 551-562, 1989.
    • (1989) Cognition , vol.17 , pp. 551-562
    • Frick, R.W.1
  • 13
    • 0023555768 scopus 로고
    • Further developments of protein secondary structure prediction using information theory
    • J. Gibrat, J. Garnier, and B. Robson, "Further developments of protein secondary structure prediction using information theory," J. Mol. Biol., vol. 198, pp. 425-443, 1987.
    • (1987) J. Mol. Biol , vol.198 , pp. 425-443
    • Gibrat, J.1    Garnier, J.2    Robson, B.3
  • 14
    • 0001327717 scopus 로고
    • Learning and extracting finite state automata with second-order recurrent neural networks
    • C. L. Giles, C. B. Miller, D. Chen, H. H. Chen, G. Z. Sun, and Y. C. Lee, "Learning and extracting finite state automata with second-order recurrent neural networks," Neural Comput., vol. 4, no. 3, pp. 393-405, 1992.
    • (1992) Neural Comput , vol.4 , Issue.3 , pp. 393-405
    • Giles, C.L.1    Miller, C.B.2    Chen, D.3    Chen, H.H.4    Sun, G.Z.5    Lee, Y.C.6
  • 15
    • 85057230110 scopus 로고    scopus 로고
    • Hierarchical recurrent neural networks for long-term dependencies
    • M. Perrone, M. Mozer, and D. D. Touretzky, Eds. Cambridge, MA: MIT Press
    • S. E. Hihi and Y. Bengio, "Hierarchical recurrent neural networks for long-term dependencies," in Advances in Neural Information Processing Systems, M. Perrone, M. Mozer, and D. D. Touretzky, Eds. Cambridge, MA: MIT Press, 1996, pp. 493-499.
    • (1996) Advances in Neural Information Processing Systems , pp. 493-499
    • Hihi, S.E.1    Bengio, Y.2
  • 16
    • 0030298864 scopus 로고    scopus 로고
    • Temporal grouping effects in immediate recall: A working memory analysis
    • G. J. Hitch, N. Burgess, J. N. Towse, and V. Culpin, "Temporal grouping effects in immediate recall: A working memory analysis," Quart. J. Exp. Psychol., vol. 49A, pp. 116-139, 1996.
    • (1996) Quart. J. Exp. Psychol , vol.49 A , pp. 116-139
    • Hitch, G.J.1    Burgess, N.2    Towse, J.N.3    Culpin, V.4
  • 17
    • 0003575034 scopus 로고
    • Untersuchungen zu dynamischen neuronalen netzen,
    • Diploma thesis, Institut fur Informatik, Technische Universitat Munchen, Munchen, Germany
    • S. Hochreiter, "Untersuchungen zu dynamischen neuronalen netzen," Diploma thesis, Institut fur Informatik, Technische Universitat Munchen, Munchen, Germany, 1991.
    • (1991)
    • Hochreiter, S.1
  • 18
    • 0000370416 scopus 로고    scopus 로고
    • Lstm can solve hard long time lag problems
    • M. C. Mozer, M. I. Jordan, and T. Petsche, Eds. Cambridge, MA: MIT Press
    • S. Hochreiter and J. Schmidhuber, "Lstm can solve hard long time lag problems," in Advances in Neural Information Processing Systems 9 M. C. Mozer, M. I. Jordan, and T. Petsche, Eds. Cambridge, MA: MIT Press, 1997, pp. 473-479.
    • (1997) Advances in Neural Information Processing Systems 9 , pp. 473-479
    • Hochreiter, S.1    Schmidhuber, J.2
  • 19
    • 0035957531 scopus 로고    scopus 로고
    • A novel method of protein secondary structure prediction with high segment overlap measure: Support vector machine approach
    • S. Hua and Z. Sun, "A novel method of protein secondary structure prediction with high segment overlap measure: Support vector machine approach," J. Mol. Biol., vol. 308, pp. 397-407, 2001.
    • (2001) J. Mol. Biol , vol.308 , pp. 397-407
    • Hua, S.1    Sun, Z.2
  • 20
    • 0033578684 scopus 로고    scopus 로고
    • Protein secondary structure prediction based on positionspecific scoring matrices
    • D. T. Jones, "Protein secondary structure prediction based on positionspecific scoring matrices," J. Mol. Biol., vol. 292, pp. 195-202, 1999.
    • (1999) J. Mol. Biol , vol.292 , pp. 195-202
    • Jones, D.T.1
  • 22
    • 0032123428 scopus 로고    scopus 로고
    • How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies
    • T. Lin, B. G. Horne, and C. L. Giles, "How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies," Neural Netw., vol. 11, pp. 861-868, 1998.
    • (1998) Neural Netw , vol.11 , pp. 861-868
    • Lin, T.1    Horne, B.G.2    Giles, C.L.3
  • 23
    • 33646241633 scopus 로고    scopus 로고
    • Learning long-term dependencies in NARX recurrent neural networks
    • Nov
    • T. Lin, B. G. Horne, P. Tino, and C. L. Giles, "Learning long-term dependencies in NARX recurrent neural networks," IEEE Trans. Neural Netw., vol. 7, no. 6, pp. 1329-1337, Nov. 1996.
    • (1996) IEEE Trans. Neural Netw , vol.7 , Issue.6 , pp. 1329-1337
    • Lin, T.1    Horne, B.G.2    Tino, P.3    Giles, C.L.4
  • 24
    • 0031675929 scopus 로고    scopus 로고
    • Fast training of recurrent networks based on the em algorithms
    • Jan
    • S. Ma and C. Ji, "Fast training of recurrent networks based on the em algorithms," IEEE Trans. Neural Netw., vol. 9, no. 1, pp. 11-26, Jan. 1998.
    • (1998) IEEE Trans. Neural Netw , vol.9 , Issue.1 , pp. 11-26
    • Ma, S.1    Ji, C.2
  • 25
    • 0016772212 scopus 로고
    • Comparison of the predicted and observed secondary structure of t4 phage lysozyme
    • B. Matthews, "Comparison of the predicted and observed secondary structure of t4 phage lysozyme," Biochim Biophys Acta, vol. 405, no. 2, pp. 442-451, 1975.
    • (1975) Biochim Biophys Acta , vol.405 , Issue.2 , pp. 442-451
    • Matthews, B.1
  • 26
    • 53149142471 scopus 로고    scopus 로고
    • What is the minimum number of residues to determine the secondary structural state
    • X. M. Pan, W. D. Niu, and Z. X.Wang, "What is the minimum number of residues to determine the secondary structural state," J. Protein Chem., vol. 18, no. 5, pp. 579-584, 1999.
    • (1999) J. Protein Chem , vol.18 , Issue.5 , pp. 579-584
    • Pan, X.M.1    Niu, W.D.2    Wang, Z.X.3
  • 27
    • 0028401031 scopus 로고
    • Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks
    • Mar
    • G. V. Puskorius and L. A. Feldkamp, "Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks," IEEE Trans. Neural Netw., vol. 5, no. 2, pp. 279-297, Mar. 1994.
    • (1994) IEEE Trans. Neural Netw , vol.5 , Issue.2 , pp. 279-297
    • Puskorius, G.V.1    Feldkamp, L.A.2
  • 28
    • 0005803728 scopus 로고
    • Static and dynamic error propagation networks with application to speech coding
    • A. J. Robinson and F. Fallside, "Static and dynamic error propagation networks with application to speech coding," in Proc. Neural Inf. Process. Syst., 1987, pp. 632-641.
    • (1987) Proc. Neural Inf. Process. Syst , pp. 632-641
    • Robinson, A.J.1    Fallside, F.2
  • 29
    • 0027291015 scopus 로고
    • Prediction of protein secondary structure at better than 70% accuracy
    • B. Rost and C. Sander, "Prediction of protein secondary structure at better than 70% accuracy," J. Mol. Biol., vol. 232, pp. 584-599, 1993.
    • (1993) J. Mol. Biol , vol.232 , pp. 584-599
    • Rost, B.1    Sander, C.2
  • 30
    • 0014514930 scopus 로고
    • Temporal grouping, rehearsal and short-term memory
    • J. Ryan, "Temporal grouping, rehearsal and short-term memory," Quart. J. Exp. Psychol., vol. 21, pp. 148-155, 1969.
    • (1969) Quart. J. Exp. Psychol , vol.21 , pp. 148-155
    • Ryan, J.1
  • 31
    • 0009234053 scopus 로고
    • Adaptive decomposition of time
    • T. Kohonen, K. Mikisara, O. Simula, and J. Kangas, Eds. New York: Elsevier
    • J. Schmidhuber, "Adaptive decomposition of time," in Artificial Neural Networks, T. Kohonen, K. Mikisara, O. Simula, and J. Kangas, Eds. New York: Elsevier, 1991, pp. 909-914.
    • (1991) Artificial Neural Networks , pp. 909-914
    • Schmidhuber, J.1
  • 32
    • 0001033889 scopus 로고
    • Learning complex, extended sequences using the principle of history compression
    • J. Schmidhuber, "Learning complex, extended sequences using the principle of history compression," Neural Comput., vol. 4, no. 2, pp. 234-242, 1992.
    • (1992) Neural Comput , vol.4 , Issue.2 , pp. 234-242
    • Schmidhuber, J.1
  • 33
    • 33749188812 scopus 로고
    • Continuous history compression
    • H. Huning, S. Neuhauser, M. Raus, and W. Ritschel, Eds
    • J. Schmidhuber, M. C. Mozer, and D. Prelinger, "Continuous history compression," in Proc. Int. Workshop Neural Netw., H. Huning, S. Neuhauser, M. Raus, and W. Ritschel, Eds., 1993, pp. 87-95.
    • (1993) Proc. Int. Workshop Neural Netw , pp. 87-95
    • Schmidhuber, J.1    Mozer, M.C.2    Prelinger, D.3
  • 34
    • 0033338205 scopus 로고    scopus 로고
    • Local gain adaptation in stochastic gradient descent
    • London, U.K
    • N. N. Schraudolph, "Local gain adaptation in stochastic gradient descent," in Proc. 9th Int. Conf. Artif. Neural Netw., London, U.K., 1999, pp. 569-574.
    • (1999) Proc. 9th Int. Conf. Artif. Neural Netw , pp. 569-574
    • Schraudolph, N.N.1
  • 35
    • 0036631778 scopus 로고    scopus 로고
    • Fast curvature matrix-vector products for secondorder gradient descent
    • N. N. Schraudolph, "Fast curvature matrix-vector products for secondorder gradient descent," Neural Comput., vol. 14, no. 7, pp. 1723-1738, 2000.
    • (2000) Neural Comput , vol.14 , Issue.7 , pp. 1723-1738
    • Schraudolph, N.N.1
  • 36
    • 0031268931 scopus 로고    scopus 로고
    • Bidirectional recurrent neural networks
    • Nov
    • M. Schuster and K. K. Paliwal, "Bidirectional recurrent neural networks," IEEE Trans. Signal Process., vol. 45, no. 11, pp. 2673-2681, Nov. 1997.
    • (1997) IEEE Trans. Signal Process , vol.45 , Issue.11 , pp. 2673-2681
    • Schuster, M.1    Paliwal, K.K.2
  • 37
    • 0001517337 scopus 로고
    • Influence of digit grouping on memory for telephone numbers
    • F. T. Severin and M. K. Rigby, "Influence of digit grouping on memory for telephone numbers," J. Appl. Psychol., vol. 47, pp. 117-119, 1963.
    • (1963) J. Appl. Psychol , vol.47 , pp. 117-119
    • Severin, F.T.1    Rigby, M.K.2
  • 38
    • 56449088476 scopus 로고    scopus 로고
    • Robust adaptive gradient-descent training algorithm for recurrent neural networks in discrete time domain
    • Nov
    • Q. Song, Y. L. Wu, and Y. C. Soh, "Robust adaptive gradient-descent training algorithm for recurrent neural networks in discrete time domain," IEEE Trans. Neural Netw., vol. 19, no. 11, pp. 1841-1853, Nov. 2008.
    • (2008) IEEE Trans. Neural Netw , vol.19 , Issue.11 , pp. 1841-1853
    • Song, Q.1    Wu, Y.L.2    Soh, Y.C.3
  • 39
    • 0141815610 scopus 로고    scopus 로고
    • Attempting to reduce the vanishing gradient effect through a novel recurrent multiscale architecture
    • S. Squartini, A. Hussain, and F. Piazza, "Attempting to reduce the vanishing gradient effect through a novel recurrent multiscale architecture," in Proc. Int. Joint Conf. Neural Netw., 2003, vol. 4, pp. 2819-2824.
    • (2003) Proc. Int. Joint Conf. Neural Netw , vol.4 , pp. 2819-2824
    • Squartini, S.1    Hussain, A.2    Piazza, F.3
  • 40
    • 0038241188 scopus 로고    scopus 로고
    • Latched recurrent neural network
    • B. Ster, "Latched recurrent neural network," Elektrotehni.ski vestnik, vol. 70, no. 1-2, pp. 46-51, 2003.
    • (2003) Elektrotehni.ski vestnik , vol.70 , Issue.1-2 , pp. 46-51
    • Ster, B.1
  • 41
    • 0037972164 scopus 로고    scopus 로고
    • A real-world rational agent: Unifying old and new AI
    • P. F. M. J. Verschure and P. Althaus, "A real-world rational agent: Unifying old and new AI," Cogn. Sci., vol. 27, pp. 561-590, 2003.
    • (2003) Cogn. Sci , vol.27 , pp. 561-590
    • Verschure, P.F.M.J.1    Althaus, P.2
  • 42
    • 0142136737 scopus 로고    scopus 로고
    • Environmentally mediated synergy between perception and behavior in mobile robots
    • P. F. M. J. Verschure, T. Voegtlin, and R. J. Douglas, "Environmentally mediated synergy between perception and behavior in mobile robots," Nature, vol. 425, pp. 620-624, 2003.
    • (2003) Nature , vol.425 , pp. 620-624
    • Verschure, P.F.M.J.1    Voegtlin, T.2    Douglas, R.J.3
  • 43
    • 84901618359 scopus 로고    scopus 로고
    • Anticipation model for sequential learning of complex sequences
    • Sequence Learning: Paradigms, Algorithms, and Applications, Berlin, Germany: Springer-Verlag
    • D. Wang, "Anticipation model for sequential learning of complex sequences," in Sequence Learning: Paradigms, Algorithms, and Applications, ser. Lecture Notes in Computer Science. Berlin, Germany: Springer-Verlag, 2000, vol. 1828, pp. 53-79.
    • (2000) ser. Lecture Notes in Computer Science , vol.1828 , pp. 53-79
    • Wang, D.1
  • 44
    • 0014088690 scopus 로고
    • Rehearsal grouping and hierarchical organization of serial position cues in short-term memory
    • W. A. Wickelgren, "Rehearsal grouping and hierarchical organization of serial position cues in short-term memory," Quart. J. Exp. Psychol. vol. 19, pp. 97-102, 1967.
    • (1967) Quart. J. Exp. Psychol , vol.19 , pp. 97-102
    • Wickelgren, W.A.1
  • 45
    • 68949217107 scopus 로고    scopus 로고
    • R. J. Williams and Zipser, Gradient based learning algorithms for recurrent connectionist networks, College Comput. Sci., Northeastem Univ., Boston, MA, Tech. Rep. NU-CCS-90-9, 1990.
    • R. J. Williams and Zipser, "Gradient based learning algorithms for recurrent connectionist networks," College Comput. Sci., Northeastem Univ., Boston, MA, Tech. Rep. NU-CCS-90-9, 1990.
  • 46
    • 40549096757 scopus 로고    scopus 로고
    • A normalized adaptive training of recurrent neural networks with augmented error gradient
    • Feb
    • Y. L. Wu, Q. Song, and S. Liu, "A normalized adaptive training of recurrent neural networks with augmented error gradient," IEEE Trans. Neural Netw., vol. 19, no. 2, pp. 351-356, Feb. 2008.
    • (2008) IEEE Trans. Neural Netw , vol.19 , Issue.2 , pp. 351-356
    • Wu, Y.L.1    Song, Q.2    Liu, S.3
  • 47
    • 0027199670 scopus 로고
    • Protein secondary structure prediction using nearest-neighbor methods
    • T. Yi and E. Lander, "Protein secondary structure prediction using nearest-neighbor methods," J. Mol. Biol., vol. 232, pp. 1117-1129, 1993.
    • (1993) J. Mol. Biol , vol.232 , pp. 1117-1129
    • Yi, T.1    Lander, E.2
  • 48
    • 0033081846 scopus 로고    scopus 로고
    • A modified definition of SOV, a segment-based measure for protein secondary structure prediction assessment
    • A. Zemla, C. Venclovas, K. Fidelis, and B. Rost, "A modified definition of SOV, a segment-based measure for protein secondary structure prediction assessment," Proteins: Structure, Function, Genetics, vol. 34, no. 2, pp. 220-223, 1999.
    • (1999) Proteins: Structure, Function, Genetics , vol.34 , Issue.2 , pp. 220-223
    • Zemla, A.1    Venclovas, C.2    Fidelis, K.3    Rost, B.4
  • 49
    • 44349110244 scopus 로고    scopus 로고
    • Global asymptotic stability of recurrent neural networks with multiple time-varying delays
    • May
    • H. G. Zhang, Z. S. Wang, and D. R. Liu, "Global asymptotic stability of recurrent neural networks with multiple time-varying delays," IEEE Trans. Neural Netw., vol. 19, no. 5, pp. 855-873, May 2008.
    • (2008) IEEE Trans. Neural Netw , vol.19 , Issue.5 , pp. 855-873
    • Zhang, H.G.1    Wang, Z.S.2    Liu, D.R.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.