Approximation of Dynamical Time-Variant Systems by Continuous-Time Recurrent Neural Networks

IEEE Transactions on Circuits and Systems II: Express Briefs

Volumn 52, Issue 10, 2005, Pages 656-660

  Li, Xiao Dong ^a,b   Ho, John K L ^a   Chow, Tommy W S ^a  

^a CITY UNIVERSITY OF HONG KONG   (Hong Kong)

^b SUN YAT SEN UNIVERSITY   (China)

Author keywords

Approximation; dynamical time variant systems; recurrent neural networks

Indexed keywords

ADAPTIVE ALGORITHMS; APPROXIMATION THEORY; BACKPROPAGATION; LEARNING SYSTEMS; RECURRENT NEURAL NETWORKS; SET THEORY; THEOREM PROVING;

CONTINUOUS-TIME RECURRENT NEURAL NETWORKS; DYNAMICAL TIME-VARIANT SYSTEMS; FINITE TIME TRAJECTORY;

TIME VARYING CONTROL SYSTEMS;

EID: 27644567803     PISSN: 15497747     EISSN: 15583791     Source Type: Journal    
DOI: 10.1109/TCSII.2005.852006     Document Type: Article

References (13)

1. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proc. Nat. Acad. Sci. USA, vol. 79, pp. 2554–2558, 1982.
2. F. J. Pineda, “Dynamics and architecture for neural computation,” J. Complexity, vol. 4, pp. 216–245, 1988.
3. K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” Neural Netw., vol. 2, no. 5, pp. 359–366, 1989.
4. K. Funahashi, “On the approximation realization of continuous mappings by neural networks,” Neural Netw., vol. 2, no. 3, pp. 183–191, 1989.
5. G. Cybenko, “Approximation by superpositions of a sigmoidal function,” Math. Control, Signal, Syst., vol. 2, pp. 303–314, 1989.
6. K. Li, “Approximation theory and recurrent networks,” in Proc. IJCNN'91, vol. 2, 1991, pp. 266–271.
7. L. Jin, P. N. Nikiforuk, and M. M. Gupta, “Approximation of discrete-time state-space trajectories using dynamic recurrent neural networks,” IEEE Trans. Autom. Control, vol. 40, no. 7, pp. 1266–1270, Jul. 1995.
8. K. Funahashi and Y. Nakamura, “Approximation of dynamical systems by continuous time recurrent neural networks,” Neural Netw., vol. 6, pp. 801–806, 1993.
9. T. W. S. Chow and X.-D. Li, “Modeling of continuous time dynamical systems with input by recurrent neural networks,” IEEE Trans. Circuit Syst. I, Fundam. Theory Appl., vol. 47, no. 4, pp. 575–578, Apr. 2000.
10. C. Kambhampati, F. Garces, and K. Warwick, “Approximation of nonautonomous dynamical systems by continuous time recurrent neural networks,” in Proc. IEEE-INNS-ENNS Int. Joint Conf., vol. 1, 2000, pp. 64–69.
11. L. K. Li, “Capacity of recurrent networks,” in Proc. IJCNN'91, vol. 3, Singapore, 1991, pp. 1330–1335.
12. B. A. Pearlmutter, “Gradient calculations for dynamic recurrent neural networks: a survey,” IEEE Trans. Neural Netw., vol. 6, no. 5, pp. 1212–1228, Sep. 1995.
13. T. W. S. Chow and Y. Fang, “A recurrent neural network based real-time learning control strategy applying to nonlinear systems with unknown dynamics,” IEEE Trans. Ind. Electron., vol. 45, no. 1, pp. 151–161, Feb. 1998.