Dynamical control by recurrent neural networks through genetic algorithms

International Journal of Adaptive Control and Signal Processing

Volumn 13, Issue 4, 1999, Pages 261-271

  Kumagai, Toru ^a   Wada, Mitsuo ^b   Hashimoto, Ryoichi ^a   Utsugi, Akio ^a  

^a NATL INST BIOSCI HUM TECHNOL   (Japan)

^b HOKKAIDO UNIVERSITY   (Japan)

Author keywords

Copy operator; Genetic algorithm; Inverted pendulum; Recurrent neural network

Indexed keywords

EID: 0347662173     PISSN: 08906327     EISSN: None     Source Type: Journal    
DOI: 10.1002/(SICI)1099-1115(199906)13:4<261::AID-ACS546>3.0.CO;2-N     Document Type: Article

References (18)

1. Kumagai, T., R. Hashimoto and M. Wada, 'Learning of limit cycles in discrete-time neural network', Neurocomputing, 13, 1-10 (1996).
2. Gardella, S., T. Kumagai, R. Hashimoto and M. Wada, 'On the dynamics and applications of a discrete time binary neural network with time delay', Intell. Fuzzy Systems., 2, 243-250 (1994).
3. Standfuss, A. and R. Eckmiller, 'To swing up an inverted pendulum using stochastic real-valued reinforcement learning', Proc. Int. Conf. on Artificial Neural Networks (ICANN '94), Vol. 1, Sorrento, 1994, pp. 655-658.
4. Huang, S. J. and C. L. Fuang, 'Control of a sliding inverted pendulum using a neural network', Int. J. Comput. Appl. Technol., 9, 67-75 (1996).
5. Rumelhart, D. E., G. E. Hinton and R. J. Williams, 'learning internal representations by error propagation', in Parallel, Distributed Processing, Vol. 1, MIT Press, Cambridge, MA, 1986, pp. 318-362.
6. Doya, K. and S. Yoshizawa, 'Adaptive neural oscillator using continuous-time back-propagation learning', Neural Networks, 2, 375-386 (1989).
7. Gomi, H. and M. Kawato, 'Neural network control for a closed-loop system using feedback error learning', Neural Networks, 6, 933-946 (1993).
8. Barto, A. G., S. J. Bradtke and S. P. Singh, 'Learning to act using real-time dynamic programming', Artif. Intell., 72, 81-138 (1995).
9. Petridis, V., S. Kazarlis and A. Papaikonomou, 'A genetic algorithm for training recurrent neural networks', Proc. 1993 Int. Joint Conf. on Neural Networks (IJCNN'93), Nagoya, 1993, pp. 2706-2709.
10. Angeline, P. J., G. M. Saunders and J. B. Pollack, 'An evolutionary algorithm that constructs recurrent neural networks', IEEE Trans. Neural Networks, 5, 54-65 (1994).
11. Kitano, H., 'Designing neural networks using genetic algorithms with graph generation system', Complex Systems, 4, 461-76 (1990).
12. Kumagai, T. et al., 'Structured learning in recurrent neural network using genetic algorithm with internal copy operator'. Proc. 1997 IEEE Int. Conf. on Evolutionary Computation (ICEC'97), Indianapolis, 1997.
13. Hopfield, J. J., 'Neural networks and physical systems with emergent collective computational abilities', Proc. Nat. Acad. Sci. 79, 2554-2558, (1982).
14. Jordan, M. I., 'Attractor dynamics and parallelism in a connectionists sequential machine', Proc. 8th Annual Conf. of the Cognitive Science Society, Amhert, 1986, pp. 531-546.
15. Elman, J. L., 'Finding structure in time', Cogn. Sci., 14, 179-211(1990).
16. Koch, C. and I. Segev, Methods in Neuronal Modeling, The MIT Press, Cambridge, MA, 1998.
17. Wang, X., 'Period-doublings to chaos in a simple neural network: An analytical proof', Complex Systems, 5, 425-441 (1991).
18. Kumagai, T. et al., 'Learning of recurrent neural networks through genetic algorithm with internal copy operator', Trans. Inst. Electron. Inf. Commun., J81-D-II, 378-385, (1998) (in Japanese).