Generalized backpropagation through time for continuous time neural networks and discrete time measurements

Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

Volumn 3070, Issue , 2004, Pages 190-196

  Fujarewicz, Krzysztof ^a   Galuszka, Adam ^a  

^a SILESIAN UNIVERSITY OF TECHNOLOGY   (Poland)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; BACKPROPAGATION; DISCRETE TIME CONTROL SYSTEMS; INTEGRATION; LEARNING SYSTEMS; MATHEMATICAL MODELS; PROBLEM SOLVING;

DATA SYSTEMS; MODIFIED ADJOINT SYSTEMS; PERFORMANCE INDEX (PI); REAL TIME RECURRENT LEARNING (RTRL);

NEURAL NETWORKS;

EID: 9444261975     PISSN: 03029743     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1007/978-3-540-24844-6_24     Document Type: Conference Paper

References (14)

1. Ahmed M. S.: Block partial derivative and its application to neural-net-based direct-model-reference adaptive control, IEE Proc.-Control Theory Appl., vol. 141, pp. 305-314, 1994.
2. Baldi P.: Gradient descent learning algorithm overview: A general dynamical systems perspective, IEEE Trans. Neural Networks, vol. 6, pp. 182-195, 1995.
3. Fujarewicz K.: Optimal control of nonlinear systems using generalized back propagation through time, Proc. Eighteenth IASTED Conference Modelling, Identification and Control, Innsbruck, Austria, February 1999.
4. Fujarewicz K.: Systems transposed in time and their application to gradient calculation in dynamical systems containing neural nets, Proc. Fourth Conference Neural Networks and Their Applications, Zakopane, Poland, May 1999.
5. Fujarewicz K.: Identification of heat exchanger using generalized back propagation through time, Proc. Nineteenth IASTED Conference Modelling, Identification and Control, pp. 267-273, Innsbruck, Austria, February 2000.
6. Fujarewicz K.: Identification and suboptimal control of heat exchanger using generalized back propagation through time, Archives of Control Sciences, vol.10(XLVI), No. 3-4. pp. 167-183.
7. Fujarewicz K.: Evaluation of a helicopter model using generalized back propagation through, in: L. Rutkowski, J. Kacprzyk (Eds.), Advances in Soft Computing Neural Networks and Soft Computing, Physica-Verlag, 2002.
8. Fujarewicz K.: On construction of an adjoint system for continuous-discrete systems, Proc. of Seminar on Electrical Engineering, pp. 56-61, Istebna, Poland, 2003.
9. Kailath T. (1980): Linear Systems, Prentice-Hall, Inc., Engelwood Cliffs, N.J.
10. Narendra S. N., Parthasarathy K.: Gradient methods for the optimization of dynamical systems containing neural networks, IEEE Trans. Neural Networks, vol. 2, pp. 252-262, 1991.
11. Pearlmutter B. A. (1995): Gradient calculations for dynamic recurrent neural networks: A survey, IEEE Trans. Neural Networks, vol. 6, pp. 1212-1228.
12. Wan E., Beaufays F.: Diagrammatic derivation of gradient algorithms for neural networks, Neural Computation, vol. 8, no. 1, January 1996, pp. 182-201.
13. Werbos P. J. (1990): Backpropagation through time: what it does and how to do it, Proc. IEEE, vol. 78, pp. 1550-1560.
14. Williams R., Zipser D.: Learning algorithm for continually running fully recurrent neural networks, Neural Computation, vol. 1, pp. 270-280, 1989.