A selected problem of the structure optimization and decomposition of the artificial neural network with cross-forward connections

• Autorzy: Płaczek S.
• Języki publikacji: EN

Abstrakty

EN

The problem of an Artificial Neural Network (ANN) structure optimization is related to the definition of the optimal number of hidden layers and the distribution of neurons between layers depending on a selected optimization criterion and inflicted constrains. Using a hierarchical structure is an accepted default way of defining an ANN structure. The following article presents the resolution of the optimization problem. The function describing the number of subspaces is given, and the minimum number of layers, as well as the distribution of neurons between layers, shall be found. The structure can be described using different methods, mathematical tools, and software or/and technical implementation. The ANN decomposition into hidden and output layers - the first step to build a two-level learning algorithm for cross-forward connections structure - is described, too.

Słowa kluczowe

EN

artificial neural network; structure optimization; decomposition; coordination; cross connection

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Computer Applications in Electrical Engineering
• Rocznik: 2014
• Tom: Vol. 12
• Strony: 597--608
• Opis fizyczny: Bibliogr. 11 poz., rys., tab.

Twórcy

autor

Płaczek S.

• Akademia Finansów i Biznesu Vistula 00-725 Warszawa, ul. Chełmska 18A/28

Bibliografia

• [1] S. Osowski, Sieci neuronowe do przetwarzania informacji, Oficyna Wydawnicza Politechniki Warszawskiej, Warszaw 2006.
• [2] O. B. Lapunow, On possibility of circuit synthesis of diverse elements, Mathematical Institut of B.A. Steklova, 1958.
• [3] Toshinori Munakate, Foundational of the New Artificial Intelligence, Second Edition, Springer 2008.
• [4] Colion Fyle, Artificial Neural Network and Information Theory, Department of Computing and Information System, The university of Paisley, 2000.
• [5] Joarder Kamruzzaman, Rezaul Begg, Artificial Neural Network in Finance and Manufacturing, Idea Group Publishing, 2006.
• [6] L. Rutkowski, metody i techniki sztucznej inteligencji, Wydawnictwo naukowe PWN, Warszawa 2006.
• [7] S. Placzek, B. Adhikari, Analysis of Multilayer Neural Network with Direct Connection Cross-forward Connection, Conference CS&P 2013 Warsaw University, Warszawa 2013.
• [8] W. Findeisen, J. Szymanowski, A. Wierzbicki, Teoria i metody obliczeniowe optymalizacji. Państwowe Wydawnictwo Naukowe, Warszawa 1977.
• [9] Ch. M. Bishop, Pattern Recognition and Machine Learning, Springer Science + Business Media, LLC 2006.
• [10] M. D. Mesarocic, D. Macko, and Y. Takahara, Theory of hierarchical multilevel systems, Academic Press, New York and London, 1970.
• [11] Zeng-Guang Hou.Madan M.Gupta, Peter N. Nikiforuk, Min Tan, and Long Cheng, A Recurrent Neural Network for Hierarchical Control of Interconnected Dynamic Systems, IEEE Transactions on Neural Networks, Vol. 18, o. 2, March 2007.