Equivalence of Conventional and Modified Network of Generalized Neural Elements
The article is devoted to the analysis of neural networks consisting of generalized neural elements. The first part of the article proposes a new neural network model — a modified network of generalized neural elements (MGNE-network). This network developes the model of generalized neural element, w...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Yaroslavl State University
2016-10-01
|
| Series: | Моделирование и анализ информационных систем |
| Subjects: | |
| Online Access: | https://www.mais-journal.ru/jour/article/view/397 |
| _version_ | 1797877852568289280 |
|---|---|
| author | E. V. Konovalov |
| author_facet | E. V. Konovalov |
| author_sort | E. V. Konovalov |
| collection | DOAJ |
| description | The article is devoted to the analysis of neural networks consisting of generalized neural elements. The first part of the article proposes a new neural network model — a modified network of generalized neural elements (MGNE-network). This network developes the model of generalized neural element, whose formal description contains some flaws. In the model of the MGNE-network these drawbacks are overcome. A neural network is introduced all at once, without preliminary description of the model of a single neural element and method of such elements interaction. The description of neural network mathematical model is simplified and makes it relatively easy to construct on its basis a simulation model to conduct numerical experiments. The model of the MGNE-network is universal, uniting properties of networks consisting of neurons-oscillators and neurons-detectors. In the second part of the article we prove the equivalence of the dynamics of the two considered neural networks: the network, consisting of classical generalized neural elements, and MGNE-network. We introduce the definition of equivalence in the functioning of the generalized neural element and the MGNE-network consisting of a single element. Then we introduce the definition of the equivalence of the dynamics of the two neural networks in general. It is determined the correlation of different parameters of the two considered neural network models. We discuss the issue of matching the initial conditions of the two considered neural network models. We prove the theorem about the equivalence of the dynamics of the two considered neural networks. This theorem allows us to apply all previously obtained results for the networks, consisting of classical generalized neural elements, to the MGNE-network. |
| first_indexed | 2024-04-10T02:23:45Z |
| format | Article |
| id | doaj.art-123ba5427ea647cfa8ca348bc2796cb9 |
| institution | Directory Open Access Journal |
| issn | 1818-1015 2313-5417 |
| language | English |
| last_indexed | 2024-04-10T02:23:45Z |
| publishDate | 2016-10-01 |
| publisher | Yaroslavl State University |
| record_format | Article |
| series | Моделирование и анализ информационных систем |
| spelling | doaj.art-123ba5427ea647cfa8ca348bc2796cb92023-03-13T08:07:34ZengYaroslavl State UniversityМоделирование и анализ информационных систем1818-10152313-54172016-10-0123565766610.18255/1818-1015-2016-5-657-666333Equivalence of Conventional and Modified Network of Generalized Neural ElementsE. V. Konovalov0Ярославский государственный университет им. П.Г. Демидова, ул. Советская, 14, г. Ярославль, 150003 РоссияThe article is devoted to the analysis of neural networks consisting of generalized neural elements. The first part of the article proposes a new neural network model — a modified network of generalized neural elements (MGNE-network). This network developes the model of generalized neural element, whose formal description contains some flaws. In the model of the MGNE-network these drawbacks are overcome. A neural network is introduced all at once, without preliminary description of the model of a single neural element and method of such elements interaction. The description of neural network mathematical model is simplified and makes it relatively easy to construct on its basis a simulation model to conduct numerical experiments. The model of the MGNE-network is universal, uniting properties of networks consisting of neurons-oscillators and neurons-detectors. In the second part of the article we prove the equivalence of the dynamics of the two considered neural networks: the network, consisting of classical generalized neural elements, and MGNE-network. We introduce the definition of equivalence in the functioning of the generalized neural element and the MGNE-network consisting of a single element. Then we introduce the definition of the equivalence of the dynamics of the two neural networks in general. It is determined the correlation of different parameters of the two considered neural network models. We discuss the issue of matching the initial conditions of the two considered neural network models. We prove the theorem about the equivalence of the dynamics of the two considered neural networks. This theorem allows us to apply all previously obtained results for the networks, consisting of classical generalized neural elements, to the MGNE-network.https://www.mais-journal.ru/jour/article/view/397нейронные сетимодели нейронных элементовобобщенный нейронный элементмонэ-сеть |
| spellingShingle | E. V. Konovalov Equivalence of Conventional and Modified Network of Generalized Neural Elements Моделирование и анализ информационных систем нейронные сети модели нейронных элементов обобщенный нейронный элемент монэ-сеть |
| title | Equivalence of Conventional and Modified Network of Generalized Neural Elements |
| title_full | Equivalence of Conventional and Modified Network of Generalized Neural Elements |
| title_fullStr | Equivalence of Conventional and Modified Network of Generalized Neural Elements |
| title_full_unstemmed | Equivalence of Conventional and Modified Network of Generalized Neural Elements |
| title_short | Equivalence of Conventional and Modified Network of Generalized Neural Elements |
| title_sort | equivalence of conventional and modified network of generalized neural elements |
| topic | нейронные сети модели нейронных элементов обобщенный нейронный элемент монэ-сеть |
| url | https://www.mais-journal.ru/jour/article/view/397 |
| work_keys_str_mv | AT evkonovalov equivalenceofconventionalandmodifiednetworkofgeneralizedneuralelements |