Identyfikatory
Warianty tytułu
Badania porównawcze metod uczenia sieci neuronowej
Języki publikacji
Abstrakty
The paper presents a comparative study of various learning methods for artificial neural network. The methods are: the backpropagation BP, the recursive least squares RLS, the Zangwill's method ZGW and the method based on evolutionary algorithm EA. The study consists of evaluating the learning effectiveness of these methods and selecting the most efficient one to be used in the designing of an adaptive neural voltage controller for a synchronous generator.
W artykule przedstawiono wyniki badań porównawczych metod uczenia sieci neuronowych takich jak: metoda propagacji wstecznej błędów, rekurencyjna metoda najmniejszych kwadratów, metoda Zangwill'a, metoda algorytmów ewolucyjnych. Celem tych badań jest dobieranie najefektywniejszej metody uczenia do projektowania adaptacyjnego neuronowego regulatora napięcia generatora synchronicznego.
Wydawca
Czasopismo
Rocznik
Tom
Strony
117--121
Opis fizyczny
Bibliogr. 20 poz., rys., wykr., wzory
Twórcy
autor
- Faculty of Electrical and Control Engineering, Gdansk University of Technology, h.tiliouine@ely.pg.gda.pl
Bibliografia
- [1] Arabas J.: Lectures on evolutionary algorithms (in Polish). WNT, Warsaw, 2001.
- [2] Bilski J.: New algorithms for learning of the feedforward neural networks. Second Conference "Neural Network and their Applications", 1996, Szczyrk-Poland, pp. 39-45.
- [3] Goldberg D. E.: Genetic algorithms in search, optimization and machine learning. - Addison-Wesley publishing Compagny, inc., 1989.
- [4] Michalewicz Z.: Genetic algorithms + data structure = Evolution programs. - Springer-Verlag, 1992.
- [5] Omatu S. , Khalid M. , Yusof R. : Neuro-Control and its Applications. - London: Springer-Verlag, 1995.
- [6] Osowski S., Bojarczak P., Stodolski M.: Fast Second Order Learning Algorithm for Feedforward Multilayer Neural Networks and its Applications. - Neural Networks, Vol. 9, No. 9, 1996, pp. 1583-1596.
- [7] Guang-Bin Huang; Qin-Yu Zhu; Chee-Kheong Siew: Real-time learning capability of neural networks, IEEE Transactions On Neural Network, vol.17, No 4, July 2006, pp. 863-878.
- [8] Prechelt L.: A Quantitative Study of Experimental Evaluations of Neural Network Learning Algorithms: Current Research Practice. - Neural Networks, Vol. 9, No. 3, 1996, pp. 457-462.
- [9] Zangwill W. I.: Minimizing a function without calculating derivatives. - The Computer Journal, Vol. 10, 1967.
- [10] Vasil'ev F. P.: Numerical methods for solving extremum problems, Moscow 1980.
- [11] Karmanov V. G.: Mathematical programming, Moscow 1975.
- [12] Yong Xu; Kwok-Wo Wong; Chi-Sing Leung: Generalized RLS approach to the training of neural networks IEEE Transactions On Neural Network, vol. 17, No 1, january 2006, pp. 19- 34.
- [13] Lubośny z., Tiliouine H.: An integrated neural-network based adaptive controller of generator and turbine unit, Międzynarodowa Konferencja SYS'95, Brno, 1995.
- [14] Lubośny Z., Tiliouine H.: Neuronowy regulator napięcia generatora synchronicznego, Międzynarodowa Konferencja APE'05, Gdańsk-Jurata, Czerwiec 1995.
- [15] Farag W. A., Quintana V. H., L-Torres G.: Applications of artificial intelligence techniques in synchronous machine control, International Journal of Engineering Intelligent Systems for Electrical Engineering an Communications, Vol. 6, No 2, June 1998.
- [16] Tanomaru J., Omatu S.: Process control by on-line trained neural controllers IEEE Transactions on Industrial Electronics, Vol.39, No 6, December 1992.
- [17] Noriega Jose R., Wang Hong: A direct neural-network control for unknown nonlinear systems and its application IEEE Transactions on Neural Networks, Vol. 9, No 1, January 1998.
- [18] Tadeusiewicz Ryszard: Sieci neuronowe, Akademicka Oficyna wydawnicza RM, Warszawa 1993.
- [19] Rutkowski Leszek: Metody i techniki sztucznej inteligencji, PWN, Warszawa 2005.
- [20] Prncipe Jose C., Euliano Neil R., Lefebvre W. Curt: Neural and adaptive systems, Fundamentals through simulations, John Wiley & Sons, INC, 2000.
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-article-BSW4-0036-0031