hrcak mascot   Srce   HID

Izvorni znanstveni članak

Dynamic Neural Network for Prediction and Identification of Nonlinear Dynamic Systems

Dubravko Majetić ; Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Zagreb, Croatia

Puni tekst: engleski, pdf (4 MB) str. 99-106 preuzimanja: 102* citiraj
APA 6th Edition
Majetić, D. (1995). Dynamic Neural Network for Prediction and Identification of Nonlinear Dynamic Systems. Journal of computing and information technology, 3 (2), 99-106. Preuzeto s https://hrcak.srce.hr/150431
MLA 8th Edition
Majetić, Dubravko. "Dynamic Neural Network for Prediction and Identification of Nonlinear Dynamic Systems." Journal of computing and information technology, vol. 3, br. 2, 1995, str. 99-106. https://hrcak.srce.hr/150431. Citirano 17.10.2019.
Chicago 17th Edition
Majetić, Dubravko. "Dynamic Neural Network for Prediction and Identification of Nonlinear Dynamic Systems." Journal of computing and information technology 3, br. 2 (1995): 99-106. https://hrcak.srce.hr/150431
Harvard
Majetić, D. (1995). 'Dynamic Neural Network for Prediction and Identification of Nonlinear Dynamic Systems', Journal of computing and information technology, 3(2), str. 99-106. Preuzeto s: https://hrcak.srce.hr/150431 (Datum pristupa: 17.10.2019.)
Vancouver
Majetić D. Dynamic Neural Network for Prediction and Identification of Nonlinear Dynamic Systems. Journal of computing and information technology [Internet]. 1995 [pristupljeno 17.10.2019.];3(2):99-106. Dostupno na: https://hrcak.srce.hr/150431
IEEE
D. Majetić, "Dynamic Neural Network for Prediction and Identification of Nonlinear Dynamic Systems", Journal of computing and information technology, vol.3, br. 2, str. 99-106, 1995. [Online]. Dostupno na: https://hrcak.srce.hr/150431. [Citirano: 17.10.2019.]

Sažetak
An attempt has been made to establish a nonlinear dynamic discrete-time neuron model, the so called Dynamic Elementary Processor (DEP). This dynamic neuron disposes of local memory, in that it has dynamic states. Based on the DEP neuron, a Dynamic Multi Layer Perceptron Neural Network is proposed to predict a time series of nonlinear chaotic system. As an another application of the proposed Dynamic Neural Network (DNN), the identification of a dynamic discrete-time nonlinear system whose measurement data are spoiled with noise is performed. To accelerate the convergence of proposed extended dynamic error back propagation learning algorithm, the momentum method is applied. The learning results are presented in terms that are insensitive to the learning data range and allow easy comparison with other learning algorithms, independent of machine architecture or simulator implementation.

Ključne riječi
discrete dynamic neuron model; dynamic error-back propagation; nonlinear signal processing; chaotic system prediction; nonlinear system identification

Hrčak ID: 150431

URI
https://hrcak.srce.hr/150431

Posjeta: 138 *