Global optimization based learning for recurrent neural networks

• Autorzy: Strzelczyk M. , Domański P. D.
• Języki publikacji: EN

Abstrakty

EN

This chapter describes the application of two different global optimization algorithms (CRS3 and the evolutionary strategy) to the problem of recurrent neural network learning. The performance has been compared with the standard multilayer perceptron with classical gradient learning strategy. The performance has been tested on different dynamic test models. The efficiency of the global optimization approach is shown.

Słowa kluczowe

EN

global optimization; evolutionary algorithm; CRS3; neural networks; learning algorithm

PL

optymalizacja globalna; algorytm ewolucyjny; sieci neuronowe; algorytm uczenia

• Wydawca: Oficyna Wydawnicza Politechniki Warszawskiej
• Czasopismo: Prace Naukowe Politechniki Warszawskiej. Elektronika
• Rocznik: 2002
• Tom: z. 139
• Strony: 163--172
• Opis fizyczny: Bibliogr. 8 poz., tab., rys., wykr.

Twórcy

autor

Strzelczyk M.

• Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska 15/19, 06-665 Warsaw, Poland

autor

Domański P. D.

• Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska 15/19, 06-665 Warsaw, Poland

Bibliografia

• 1. Osowski S.: Nural networks in algorithmic approach, WNT, Warszawa 1996, (in Polish).
• 2. Osowski S.: Nural networks in information processing, PW Press, Warszawa 2000, (in Polish).
• 3. Findeisen W., Szymanowski J., Wierzbicki A.: Theory and computing methods of optimization, PWN, Warszawa, 1980, (in Polish).
• 4. Niewiadomska-Szynkieiwcz E.: the survey of global optimization algorithms, (in Polish).
• 5. Pearlmutter B.A.: Dynamic recurrent neural networks.
• 6. Proce W.L.: Global optimization algorithms for a CAD workstation, Journal of Optimization Theory and Applications, vol. 55, no 1, 1987.
• 7. Santini S., Del Bimbo A., Jain R.: Block-structured recurrent neural networks.
• 8. Box G.E.P., Jenkins G.M.: Time series analysis. Prediction and control, PWN, 1983 (in Polish).