Back
Neural network structure optimization algorithm
Authors:
- Grzegorz Nowakowski,
- Yaroslaw Dorogyy,
- Olena Doroga-Ivaniuk
Abstract
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.
- Record ID
- CUTde85e97783ed4a5abf69fe810d95caa6
- Publication categories
- ;
- Author
- Journal series
- Journal of Automation, Mobile Robotics and Intelligent Systems, ISSN 1897-8649, e-ISSN 2080-2145
- Issue year
- 2018
- Vol
- 12
- No
- 1
- Pages
- 5-13
- Other elements of collation
- rys.; tab.; wykr.; Bibliografia (na s.) - 12-13; Bibliografia (liczba pozycji) - 35; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 12, No. 1
- Keywords in English
- structure optimization, neural network, ReLU, SGD
- DOI
- DOI:10.14313/JAMRIS_1-2018/1 Opening in a new tab
- URL
- http://www.jamris.org/57-issue-01-2018 Opening in a new tab
- Related project
- Innowacyjne systemy automatyki. . Project leader at PK: , ,
Działalność statutowa - Language
- eng (en) English
- License
- Score (nominal)
- 12
- Publication indicators
- Citation count
- 12
- Additional fields
- Indeksowana w: Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUTde85e97783ed4a5abf69fe810d95caa6/
- URN
urn:pkr-prod:CUTde85e97783ed4a5abf69fe810d95caa6
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.