Multiobjective learning of complex recurrent neural network

• Autorzy: Drapała J. , Brzostowski K. , Tomczak J.
• Języki publikacji: EN

Abstrakty

EN

Modeling of complex systems requires specific methods of model assessment. Local assessment of the model of complex system reduces to independent evaluations of quality of its parts. However, such a procedure does not necessarily lead to an optimal model of the whole complex system. To do this, global assessment should be used because it takes into account connections between elements. It is also possible to combine these two approaches. In this work, we make use of multiobjective approach to assess quality of model of complex system. Complex neural network is used as a model of dynamic complex system. As an example of complex dynamic system for experimental purposes, chemical process is considered.

Słowa kluczowe

EN

complex systems; complex neural network; multiobjective learning

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Systems Science
• Rocznik: 2009
• Tom: Vol. 35, no 4
• Strony: 27--37
• Opis fizyczny: Bibliogr. 20 poz., wykr.

Twórcy

autor

Drapała J.

autor

Brzostowski K.

autor

Tomczak J.

• Wroclaw University of Technology Wyb. Wyspiańskiego 27, 50-370 Wroclaw, Poland,

Bibliografia

• [1] Bubnicki Z., Global modeling and identification of network systems, Proc. of 18th International Conference on Systems Engineering, Wright State University, Dayton, USA, 1984.
• [2] Boccara N., Modeling Complex Systems, Springer-Verlag, New York, Inc., 2004.
• [3] Drapała J., Świątek, J., Modeling of dynamic complex systems by neural networks, Proc. of 18th International Conference on Systems Engineering ICSE, Coventry University, UK, 2006, pp. 109-112.
• [4] Drapała J., Convergence of algorithm of neural networks learning for global modeling of complex systems, Proc. of 16th International Conference on Systems Science ICSS, Wroclaw University of Technology, Poland, 2007, pp. 359-368.
• [5] Drapała J., Świątek J., Backpropagation through time for learning of interconnected neural networks - identification of complex systems. Proc. of 19th International Conference on Systems Engineering ICSEng (pp. 165-170). Computer Society [Press], Las Vegas, Nevada, USA, 2008.
• [6] Drapała J., Świątek J., Brzostowski K., Stable learning algorithm of global neural network for identification of dynamic complex systems, Lecture Notes in Computer Science, Lecture Notes in Artificial Intelligence, Vol. 5097, 2008, pp. 17-27.
• [7] Ehrgott M., Multicriteria Optimization, Springer-Verlag, Berlin-Heidelberg, 2005.
• [8] Gupta M.M., Jin L., Homma N., Static and dynamic neural networks -from fundamentals to advanced theory, IEEE Press, Wiley-Interscience, A John Wiley & Sons Inc., Hoboken, New Jersey, 2003.
• [9] Ioannou P.A., Pitsillides A. (eds.), Modeling and Control of Complex Systems, Control Engineering Series, Taylor & Francis Group, LLC, 2008.
• [10] Jurgen J., Dynamical Systems - Examples of Complex Behaviour, Springer-Verlag, Berlin-Heidelberg, 2005.
• [11] Ku C.C., Lee K.Y., Diagonal recurrent neural networks for dynamic systems control, IEEE Trans, on Neural Networks, 6(1), January 1995, 144-155.
• [12] Nelles O., Nonlinear system identification -from classical approaches to neural networks and fuzzy models, Springer-Verlag, Berlin-Heidelberg, 2001.
• [13] Świątek J., Global and local modeling of complex input output systems, Proc. of 16th International Conference on Systems Engineering, Coventry University, UK, 2003, pp. 669-671.
• [14] Świątek J., Globally optimal model of complex systems -identification algorithm for cascade structure, Proc. of 15th International Conference on Systems Science, Wrocław University of Technology, Poland, 2004, pp. 367-376.
• [15] Świątek J., Selected problems of static complex systems identification, Wrocław University of Technology Publishing House, 2009, (in Polish).
• [16] Werbos P.J., Backpropagation through time: What it does and how to do it, Proc. IEEE, Vol. 78, October 1990, pp. 1550-1560.
• [17] Osowski S., Modeling and simulation of dynamic systems and processes, Warsaw University of Technology Publishing House, 2007, (in Polish).
• [18] Tur J.M., Qualitative Modelling of Complex Systems by Means of Fuzzy Inductive Reasoning Variable Selection and Search Space Reduction, PhD Thesis, Universitat Politècnica de Catalunya, Barcelona, 2001.
• [19] Yaochu J., Bernhard S., Pareto-Based Multiobjective Machine Learning: An Overview and Case Studies, IEEE Trans, on Systems, Man, and Cybernetics - Part C: Applications and Reviews, Vol. 38, No. 3, May 2008, pp. 397-415.
• [20] Yaneer B., Dynamics of Complex Systems, Addison Wesley Longman, Inc., 1997.