Classification of temporal sequences via prediction using the simple recurrent neural network

Pattern Recognition

Volumn 33, Issue 10, 2000, Pages 1759-1770

  Gupta, Lalit ^a   McAvoy, Mark ^a   Phegley, James ^a  

^a Southern Illinois University Carbondale   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MULTILAYER NEURAL NETWORKS; OBJECT RECOGNITION; VECTORS;

TEMPORAL SEQUENCES;

RECURRENT NEURAL NETWORKS;

EID: 0034301714     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(99)00149-1     Document Type: Article

References (38)

1. K.J. Lang A.H. Waibel A time-delay neural network architecture for isolated word recognition Neural Networks 3 1990 23 43
2. A. Waibel Modular construction of time delay neural networks for speech recognition Neural Comput. 1 1989 39 446
3. J.L. Elman D. Zipser Learning the hidden structure of speech J. Acoust. Soc. Amer. 83 1988 1615 1626
4. B.R. Kammerer W.A. Kupper Experiments for isolated-word recognition with single- and two-layer perceptrons Neural Networks 3 6 1990 693 706
5. W.Y. Chen Y.F. Liao S.H. Chen Speech recognition with hierarchical recurrent neural networks Pattern Recognition 28 6 1995 795 805
6. L. Gupta J. Wang A. Charles P. Kisatsky Three-layer perceptron based classifiers for the partial shape classification problem Pattern Recognition 27 1 1994 91 97
7. L. Gupta T. Sortrakul A. Charles P. Kisatsky Robust automatic target recognition using a localized boundary representation Pattern Recognition 28 10 1995 1587 1598
8. N. Ayache O.D. Faugeras HYPER A new approach for the recognition and positioning of two-dimensional objects IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8 1 1986 44 54
9. L. Gupta K. Malakapalli Robust partial shape classification using invariant breakpoints and dynamic alignment Pattern Recognition 23 10 1990 1103 1111
10. L. Gupta A.M. Upadhye Non-linear alignment of neural net outputs for partial shape classification Pattern Recognition 24 10 1991 943 948
11. T.F. Knoll R.C. Jain Recognizing partially visible objects using feature indexed hypotheses IEEE J. Robotics Automat. RA-2 1 1986 3 13
12. T.J. Sejnowski, C.R. Rosenberg, NETtalk: a parallel network that learns to read aloud, Technical Report JHU/EECS-86/01, John Hopkins University, Baltimore, January 1986.
13. A.S. Lapedes R. Faber How neural networks work Dana Z. Anderson Neural Information Processing Systems 1988 American Institute of Physics New York 442 456
14. D.E. Rumelhart G.E. Hinton R.J. Williams Learning internal representations by error propagation D.E. Rumelhart J.L. McClelland Parallel and Distributed Processing Vol. I 1986 MIT Press Cambridge, MA (Chapter 8)
15. P.J. Werbos, Backpropagation through time: what it does and how it does it, Proceedings of the IEEE, 78 (1990) 1550–1560.
16. F.J. Pineda Generalization of backpropagation to recurrent and higher order neural networks Dana Z. Anderson Neural Information Processing Systems 1988 American Institute of Physics New York 602 611
17. L.B. Almeida Backpropagation in perceptrons with feedback R. Eckmiller C. von der Malsburg Neural Computers 1988 Springer Berlin 199 208
18. B.A. Pearlmutter Learning state space trajectories in recurrent neural networks Neural Comput. 1 2 1989 263 269
19. A.M. Loger, E.M. Corwin, W.J.B. Oldham, A comparison of recurrent neural network algorithms, Proceedings of IEEE International Conference of Neural Networks, San Francisco, Vol. II, 1993, pp. 1129–1134.
20. R.J. Williams D. Zipser A learning algorithm for continually running fully recurrent neural networks Neural Comput. 1 2 1989 270 280
21. M.I. Jordan, Supervised learning systems with excess degrees of freedom, Massachusetts Institute of Technology, COINS Technical Report 88-27, May 1988.
22. R.F. Port Representation and recognition of temporal patterns Connection Sci. 1–2 1990 15 76
23. J.L. Elman Finding structure in time Cognitive Sci. 14 1990 179 211
24. J.L. Elman Distributed representations, simple recurrent networks, and grammatical inference Mach. Learning 7 2/3 1991 19 121
25. A. Cleeremans D. Servan-Schreiber J.D. McClelland Finite state automata and simple recurrent networks Neural Comput. 1 3 1989 372 381
26. J. Ghosh, V. Karamcheti, Sequence learning with recurrent networks: analysis of internal representations, Sci. Artif. Neural Networks SPIE Vol. 1710, (1992) 449–460.
27. D. Wang X. Liu S.C. Ahalt On temporal generalization of simple recurrent networks Neural Networks 9 7 1996 1099 1118
28. L. Gupta, M. McAvoy, Investigating the prediction capabilities of the simple recurrent neural network on temporal sequences, Pattern Recognition (1999) in press.
29. R. Blake, Analysis of sequence prediction in recurrent neural networks, M.S. Thesis, Department of Electrical Engineering, Southern Illinois University, Carbondale, 1996.
30. M.W. Koch R.L. Kashyap Using polygons to recognize and locate partially occluded objects IEEE Trans. Pattern Anal. Mach. Intell. PAMI-9 4 1987 483 494
31. J.W. Gorman O.R. Mitchell F.P. Kuhl Partial shape recognition using dynamic programming IEEE Trans. Pattern Anal. Mach. Intell. PAMI-10 2 1988 257 266
32. H.C. Liu M.D. Srinath Partial shape classification using contour matching in distance transformation IEEE Trans. Pattern Anal. Mach. Intell. PAMI-12 11 1990 1072 1079
33. J.L. Turney T.N. Mudge R.A. Volz Recognizing partially occluded parts IEEE Trans. Pattern Anal. Mach. Intell. PAMI-7 4 1985 410 421
34. S. Judd P.W. Munro Nets with unreliable hidden nodes learn error-correcting codes S.J. Hanson J.D. Cowan C.L. Giles Advances in Neural Information Processing Systems Vol. 5 1993 Morgan Kaufmann San Mateo, CA 89 96
35. A.F. Murray P.J. Edwards Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training IEEE Trans. Neural Networks 5 1994 792 802
36. K.-C. Jim C.L. Giles B.G. Horne An analysis of noise in recurrent neural networks convergence and generalization IEEE Trans. Neural Networks 7 6 1996 1424 1438
37. L. Gupta M.R. Sayeh R. Tammana A neural network approach to robust shape classification Pattern Recognition 23 6 1990 563 568
38. C.L. Giles C. Omlin Pruning recurrent neural networks for improved generalization performance IEEE Trans. Neural Networks 5 5 1994 848 851