Recurrent neural networks: A constructive algorithm, and its properties

Neurocomputing

Volumn 15, Issue 3-4, 1997, Pages 309-326

  Tsoia, Ah Chung ^a   Tan, Shaohua ^b  

^a UNIVERSITY OF WOLLONGONG   (Australia)

^b NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Convergence proof; Modified least squares algorithm; Online learning algorithm; Radial basis function; Recurrent neural networks

Indexed keywords

CONVERGENCE OF NUMERICAL METHODS; FUNCTIONS; LEARNING ALGORITHMS; LEARNING SYSTEMS; LEAST SQUARES APPROXIMATIONS; ONLINE SYSTEMS; THEOREM PROVING;

RADIAL BASIS FUNCTIONS; RECURRENT NEURAL NETWORKS;

NEURAL NETWORKS;

ALGORITHM; ARTICLE; LEARNING; MATHEMATICAL MODEL; NERVE CELL NETWORK; POSITIVE FEEDBACK; PRIORITY JOURNAL;

EID: 0031171305     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(97)00011-8     Document Type: Article

References (18)

1. A.D. Back, A.C. Tsoi, FIR and IIR synapses, a new neural network architecture for time series modelling, Neural Comput. 3 (1991) 375-385.
2. J. Elman, Finding structure in time, Cognitive Sci. 14 (1990) 179-211.
3. P. Frasconi, M. Gori, G. Soda, Local feedback multilayered networks, Neural Comput. 4 (1992) 120-130.
4. S. Geva, J. Sitte, A constructuve method for multivariate function approximation by multilayer preceptrons, IEEE Trans Neural Networks 3 (1992) 621-624.
5. G. Goodwin, K.S. Sin, Adaptive Filtering, Prediction and Control, Prentice-Hall, Englewood Cliffs, NJ, 1984.
6. M. Gori, M. Maggini, G. Soda, Insertion of finite state automata into recurrent radial basis function networks, preprint, 1993.
7. A. Lapedes, R. Farber, Nonlinear signal processing using neural networks: prediction and system modelling, LA-UR-262, Los Alamos National Laboratory, Los Alamos, 1987.
8. J. Moody, C. Darken, Learning with localized receptive fields, in: D. Touretzky, G. Hinton, T. Sejnowski (Eds.), Proc Connectionist Models Summer School 1988, Morgan Kaufmann, San Mateo, 1989, pp. 133-143.
9. O. Nerrand, P. Roussel-Ragot, L. Personnaz, G. Dreyfus, S. Marocs, Neural networks and nonlinear adaptive filtering: unifying concepts and new algorithms, Neural Comput. 5 (1993) 165-199.
10. S. Omohundro, Bumptrees for efficient function constraint, and classification learning, in: R.P. Lippmann, J. Moody, D. Touretzky (Eds.), Advances in Neural Information Processing Systems 3, Morgan Kaufmann, San Meteo, CA, 1991, pp. 693-699.
11. M. Powell, Radial basis functions for multivariable interpolation: a review, Technical Report DAMPT/NA 12, Dept. of Applied Maths and Theoretical Phys., University of Cambridge, 1985.
12. B. De Vries, J. Principe, A theory for neural networks with time delays, in: R. Lippmann (Ed.), Advances in Neural and Information Processing Systems, 3, 1991, pp 162-168.
13. S. Renals, Speech and neural network dynamics, Ph.D. Thesis, University of Edinburgh, 1990.
14. J. Park, I. Sandberg, Universal approximation using radial basis function networks, Neural Comput. 3 (1990) 246-257.
15. A.C. Tsoi, A.D. Back, Discrete time recurrent neural network architectures, a unifying review, Neurocomputing, accepted.
16. A.C. Tsoi, A.D. Back, Locally recurrent globally feedforward networks, a critical review of architectures, IEEE Trans. Neural Networks 5 (1994) 229-239.
17. C. Van Loan, G. Golub, Matrix Computations, North Oxford Academic Press, Oxford, 1983.
18. R.J.Williams, D. Zipser, A learning algorithm for continually running fully recurrent neural networks, Neural Comput. 1(2) (1989) 270-280.