Universal learning network and its application to chaos control

Neural Networks

Volumn 13, Issue 2, 2000, Pages 239-253

  Hirasawa, Kotaro ^a   Wang, Xiaofeng ^a   Murata, Junichi ^a   Hu, Jinglu ^a   Jin, Chunzhi ^a  

^a KYUSHU UNIVERSITY   (Japan)

Author keywords

Chaos; Higher order derivatives calculation; Lyapunov exponent; Neural networks; Universal learning networks

Indexed keywords

BACKPROPAGATION; CHAOS THEORY; DIFFERENTIAL EQUATIONS; LEARNING ALGORITHMS; LEARNING SYSTEMS; LYAPUNOV METHODS; MATHEMATICAL MODELS; NONLINEAR CONTROL SYSTEMS; REAL TIME SYSTEMS;

BACKPROPAGATION THROUGH TIME (BPTT); CHAOS CONTROL; REAL TIME RECURRENT LEARNING (RTRL); UNIVERSAL LEARNING NETWORKS (ULN);

RECURRENT NEURAL NETWORKS;

ARTICLE; CALCULATION; CHAOTIC DYNAMICS; COMPUTER SIMULATION; CONTROL; LEARNING; MODEL; NERVE CELL NETWORK; PRIORITY JOURNAL;

ARTIFICIAL INTELLIGENCE; NONLINEAR DYNAMICS;

EID: 0034000787     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(99)00100-8     Document Type: Article

References (36)

1. Aihara K., Takabe T., Toyoda M. Chaotic neural networks. Physics Letters A. 144:1990;333-340.
2. Buntine W.L., Weigend A.S. Computing second derivatives in feed-forward network: a review. IEEE Transaction on Neural Networks. 5:1994;480-488.
3. Chen L., Aihara K. Chaotic simulated by a neural network model with transient chaos. Neural Networks. 8:1995;915-930.
4. Chen G., Lai D. Making a dynamic system chaotic, feedback control of Lyapunov exponents for discrete time dynamical systems. IEEE-CAS I. 44:1997;250-253.
5. Chen G., Lai D. Anticontrol of chaos via feedback. Proceedings of IEEE conference on decision and control 1997, San Diego. 1997;367-372.
6. Chen G., Lai D. Feedback anticontrol of discrete chaos. International Journal of Bifurcation and Chaos. 8:1998;1585-1590.
7. Falcioni M., Isola S., Vulpiani A. Correlation functions and relaxation properties in chaotic dynamics and statistical mechanics. Physics Letters A. 144:1990;234-240.
8. Han M., Hirasawa K., Ohbayashi M., Fujita M. Modeling dynamic systems using universal learning network. Proceedings of IEEE conference on systems, man and cybernetics, Beijing. 5:1996;1172-1177.
9. Han M., Hirasawa K., Hu J., Murata J. Generalization ability of Universal Learning Network by using second order derivatives. Proceedings of IEEE international conference on systems, man, cybernetics, San Diego. 1998;1818-1823.
10. Hirasawa K., Ohbayashi M., Murata J. Universal Learning Network and computation of its higher order derivatives. Proceedings of IEEE international conference on neural networks, Perth. 1995;1273-1277.
11. Hirasawa K., Ohbayashi M., Fujita F., Koga M. Universal learning networks. Transactions of the Institute of Electronic Engineers of Japan. 116-C:(7):1996;794-801. in Japanese.
12. Hirasawa K., Ohbayashi M., Koga M., Harada M. Forward propagation Universal Learning Network. Proceedings of IEEE international conference on neural networks, Washington, DC. 1996;353-358.
13. Hirasawa K., Misawa J., Murata J., Ohbayashi M., Hu J. Clustering control of Chaos Universal Learning Network. Proceedings of IEEE conference on neural netwroks, Anchorage. 1998;1482-1487.
14. Hirasawa K., Wang X., Murata J., Hu J. Chaos control using maximum Lyapunov number of Universal Learning Network. Proceedings of IEEE international conference on systems, man, cybernetics, San Diego. 1998;1702-1707.
15. Hopfield J.J. Neural networks and physical systems with emergent collective computational abilities. Proceedings of National Academy of Science (USA). 1982;2554-2558.
16. Ikeda K., Matsumoto K. High-dimensional chaotic behavior in systems with time-delay feedback. Physica D. 29:1987;223-235.
17. Isermann R., Ernst S., Nelles O. Identification with dynamic neural networks - architecture, comparisons, applications. Proceedings of the 11th IFAC symposium on system identification, Kitakyushu. 3:1997;997-1022.
18. Jang J.S.R., Sun C.T. Neuro-fuzzy modeling and control. Proceedings of the IEEE. 83:(3):1995;378-406.
19. Kalman R.E. Nonlinear aspect of sampled-data control systems. Proceedings on nonlinear circuit analysis. 1956;273-313.
20. Kocaver L., Ogorzalek M. Transition in dynamical regime by driving - a method of control and synchronization of chaos. International Journal of Bifurcation and Chaos. 3:1993;479-483.
21. Lin E.T., Dayhoff J.E., Ligomenides P.A. Trajectory production with the adaptive time-delay neural network. Neural networks. 8:(3):1995;447-461.
22. McCulloch W.S., Pitts W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics. 5:1943;115-133.
23. Moody J., Darken C.J. Fast learning in networks of locally tuned processing units. Neural Computation. 1:1989;281-294.
24. Ogorzalek M. Chaos control - how to avoid chaos or take advantage of it. Journal of the Franklin Institute. 331B:(6):1994;681-704.
25. Ohbayashi M., Hirasawa K., Hashimoto M., Murata J. Robust control using second order derivative of Universal Learning Network. Proceedings of IEEE international conference on systems, man, cybernetics, Beijing. 1996;1184-1189.
26. Ohbayashi M., Hirasawa K., Murata J., Harada M. Robust learning control using Universal Learning Network. Proceedings of IEEE international conference on neural networks, Washington, DC. 1996;2208-2213.
27. Ott E., Grebogi C., Yorke J.A. Controlling chaos. Physics Review Letters. 64:1990;1196-1199.
28. Pyragas K. Continuous control of chaos by self-controlling feedback. Physics Letters A. 170:1992;421-428.
29. Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review. 65:1958;386-408.
30. Rumelhart D.E., McClelland J.L. Parallel distributed processing. 1986;MIT Press, Cambridge, MA.
31. Shimizu K. Theory and computational method of optimal control. 1994;Korona, Tokyo. in Japanese.
32. Shinbrot T., Grebogi C., Ott E., York J.A. Using small perturbation to control chaos. Nature. 362:(3):1993;411-417.
33. Wang Y.J., Lin C.T. A second order learning algorithm for multilayer networks based on block Hessian matrix. Neural Networks. 11:1998;1607-1622.
34. Werbos, P. (1974). Beyond regression: new tools for prediction and analysis in the behavior science. Unpublished doctoral dissertation, Harvard University.
35. Williams R.J., Zipser D. A learning algorithm for continually running fully recurrent neural networks. Neural Computation. 1:(2):1989;270-280.
36. Williams, R.J., Zipser, D. (1990). Gradient-based learning algorithms for recurrent connectionist networks, College of Computer Science Technical Report No. NU-CCS-90-9, Northeastern University.