The realisation of neural network structural optimization algorithm / Grzegorz Nowakowski, Yaroslaw Dorogyy, Olena Doroga-Ivaniuk // W: Proceedings of the 2017 Federated Conference on Computer Science ... więcej

The realisation of neural network structural optimization algorithm / Grzegorz Nowakowski, Yaroslaw Dorogyy, Olena Doroga-Ivaniuk // W: Proceedings of the 2017 Federated Conference on Computer Science and Information Systems, September 3-6, 2017, Prague, Czech Republic [Dokument elektroniczny] / eds. Maria Ganzha, Leszek Maciaszek, Marcin Paprzycki. – New York City : Institute of Electrical and Electronics Engineers ; Warszawa : Polskie Towarzystwo Informatyczne, 2017. – (Annals of Computer Science and Information Systems, ISSN 2300-5963 ; 11). – S. 1365-1371 : il. (w tym kolor.). – Tryb dostępu: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8104732. – Bibliogr. 31 poz., Abstr. – Tyt. źródła wg okł. – doi: 10.15439/2017F448. – ISBN 978-83-946253-7-5 (Web). – ISBN 978-83-946253-8-2 (USB). – ISBN 978-83-946253-9-9 (ART)

This paper presents a deep analysis of literature on the problems of optimization of parameters and structure of the neural networks and the basic disadvantages that are present in the observed algorithms ... więcej

This paper presents a deep analysis of literature on the problems of optimization of parameters and structure of the neural networks and the basic disadvantages that are present in the observed algorithms and methods. As a result, there is suggested a new algorithm for neural network structure optimization, which is free of the major shortcomings of other algorithms. The paper describes a detailed description of the algorithm, its implementation and application for recognition problems.