Selected problem of structure optimization for Artificial Neural Networks with forward connections

• Autorzy: Płaczek S.
• Konferencja: Computer Applications in Electrical Engineering 2014 (28-29.04.2014; Poznań, Polska)
• Języki publikacji: EN

Abstrakty

EN

The problem of Artificial Neural Network (ANN) structure optimization related to the definition of optimal number of hidden layers and distribution of neurons between layers depending on selected optimization criterion and inflicted constrains. The 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.

Słowa kluczowe

EN

artificial neural network; network structure; structure optimization

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Poznan University of Technology Academic Journals. Electrical Engineering
• Rocznik: 2014
• Tom: No. 80
• Strony: 191--197
• Opis fizyczny: Bibliogr. 8 poz., rys., tab.

Twórcy

autor

Płaczek S.

• Akademia Finansów i Biznesu Vistula w Warszawie

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] A.Marciniak, J.Korbicz, J.Kus, Wstępne przetwarzanie danych, Sieci Neuronowe tom 6. Akademicka Oficyna Wydawnicza EXIT 2000.
• [7] L. Rutkowski, metody i techniki sztucznej inteligencji, Wydawnictwo naukowe PWN, Warszawa 2006.
• [8] S. Placzek, B. Adhikari, Analysis of Multilayer Neural Network with Direct Connection Cross-forward Connection, Conference CS&P 2013 Warsaw University, Warszawa 2013.