Autonomous learning algorithm for fully connected recurrent networks

Neurocomputing

Volumn 63, Issue SPEC. ISS., 2005, Pages 25-44

  Leclercq, Edouard ^a   Druaux, Fabrice ^a   Lefebvre, Dimitri ^a   Zerkaoui, Salem ^a  

^a UNIVERSITY OF LE HAVRE   (France)

Author keywords

Adaptive learning rate; Asymptotic stability; Recurrent network; RTRL

Indexed keywords

DATA REDUCTION; NEURAL NETWORKS; PARAMETER ESTIMATION; PERTURBATION TECHNIQUES; TIME SERIES ANALYSIS;

ADAPTIVE LEARNING; DYNAMICAL BEHAVIOURS; GRADIENT-BASED ADAPTATION; LEARNING RATES;

LEARNING ALGORITHMS;

ADAPTATION; ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; CONTROLLED STUDY; LEARNING; MATHEMATICAL ANALYSIS; MATHEMATICAL COMPUTING; NERVE CELL; NONLINEAR SYSTEM; PREDICTION; PRIORITY JOURNAL; SIMULATION; TIME SERIES ANALYSIS;

EID: 12144260517     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2004.04.007     Document Type: Article

References (24)

1. W.F. Chang M.W. Mak A conjugate gradient learning algorithm for recurrent neural networks Neurocomputing 24 1-3 1999 173-189
2. T. Chu C. Zhang Z. Zhang Necessary and sufficient conditions for absolute stability of normal NN Neural networks 16 2003 1223-1227
3. K. Doya, Bifurcations in the learning of recurrent neural networks, Proceedings of the IEEE International Symposium on Circuits and Systems, 1992, pp. 2777-2780.
4. K. Doya S. Yoshizawa Adaptive neural oscillator using continuous-time back-propagation learning Neural Networks 2 1989 375-385
5. F. Druaux E. Rogue A. Faure Constrained RTRL to reduce learning rate and forgetting phenomenon Neural Process. Lett. 7 1998 161-167
6. V.T.S. Ellamayar Y.C. Shin State estimation of continuous-time radial basis function networks Automatica 36 2000 399-407
7. L.T. Grujic Consistent Lyapunov methodology for Hopfield fuzzy neural networks Neural Parallel Sci. Comput. 7 1999 195-201
8. L.T. Grujic A.N. Michel Exponential stability and trajectory bounds of neural networks under structural variations IEEE Trans. Circuits Syst. 38 10 1991 1182-1192
9. L.T. Grujic A.N. Michel Modeling and qualitative analysis of continuous-time NN under pure structural variations Math. comput. simulat. 40 1996 523-533
10. Y. Hayashi Oscillatory neural network and learning of continuous transformed patterns Neural Networks 7 2 1994 219-231
11. J.O. Jang G.J. Jeon A parallel neuro-controller for DC motors containing nonlinear friction Neurocomputing 30 2000 233-248
12. E. Leclercq, F. Druaux, D. Lefebvre, Autonomous learning algorithm for fully connected recurrent networks, Proceedings of the ESANN'2003 European Symposium on Artificial Neural Networks, Bruges, 2003, pp. 375-381.
13. F.L. Lewis A. Yesildirek K. Liu Multilayer Neural-Net Robot Controller with guaranteed tracking performance IEEE Trans. Neural Networ. 7 2 1996 388-399
14. M.W. Mak K.W. Ku Y.L. Lu On the improvement of the real time recurrent learning algorithm for recurrent NN Neurocomputing 24 1-3 1999 13-36
15. K.S. Narendra K. Parthasarathy Identification and control of dynamical systems using neural networks IEEE Trans. Neural Networ. 1 1 1990 4-27
16. J.J. Steil Local stability of recurrent networks with time varying weights and inputs Neurocomputing 48 2002 39-51
17. W.A. Truccolo G. Rangarajan Y. Chen M. Ding Analyzing stability of equilibrium points in neural networks: A general approach Neural Networks 16 2003 1453-1460
18. R.-J. Wai H.-H. Lin F.-J. Lin Hybrid controller using fuzzy NN for identification and control of induction servo motor drive Neurocomputing 35 2000 91-112
19. D. Wang P. Bao Enhancing the estimation of plant Jacobian for adaptive neural inverse control Neurocomputing 34 2000 99-115
20. A.S. Weigend A. Gershenfeld Time Series Prediction Forecasting the Future and Understanding the Past 1994 Addison-Wesley Reading, MA
21. R.J. Williams, Adaptive State Representation and Estimation Using Recurrent Connectionnist Networks, Miller, Satten, Webos, NN for Control, MIT Press, Cambridge, 1990.
22. R.J. William D. Zipser A learning algorithm for continually running fully recurrent neural networks Neural Comput. 1 1989 270-280
23. R.J. William D. Zipser Experimental analysis of the recurrent learning algorithm Connect. Sci. 1 1989 87-111
24. D. Zipser A subgrouping strategy that reduces complexity and seeds up learning in recurrent networks Neural Comput. 1 1989 552-560