The wave model of artificial neural network
The article deals with the modeling of artificial neural networks as a system of information transmission. The analysis of the existing theoretical approaches to the optimization of the structure and training of neural networks is carried out. The proposed model is based on the commonality of decodi...
Gorde:
| Egile Nagusiak: | , , , , , , , |
|---|---|
| Formatua: | Статья |
| Hizkuntza: | English |
| Argitaratua: |
Institute of Electrical and Electronics Engineers Inc.
2020
|
| Gaiak: | |
| Sarrera elektronikoa: | https://dspace.ncfu.ru/handle/20.500.12258/12084 |
| Etiketak: |
Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|
| id |
ir-20.500.12258-12084 |
|---|---|
| record_format |
dspace |
| spelling |
ir-20.500.12258-120842020-07-29T09:40:28Z The wave model of artificial neural network Vershkov, N. A. Вершков, Н. А. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Babenko, M. G. Бабенко, М. Г. Artificial neural network Correlation function Spectral analysis Data communication systems The article deals with the modeling of artificial neural networks as a system of information transmission. The analysis of the existing theoretical approaches to the optimization of the structure and training of neural networks is carried out. The proposed model is based on the commonality of decoding processes in information transmission systems and clustering processes in neural networks. In the process of building a neuron model, we consider the well-known problem of determining the bandwidth capacity of the communication channel with noise in the geometric terms and its adaptation to the problem of assigning the input signal to a certain cluster. A neuron is considered to be a universal network element capable of performing orthogonal transformations, filtering, and other transformations of the input sequence. The layer of neurons is considered as an information converter with a certain kernel for solving the problems of orthogonal transformation, matched filtering, and nonlinear transformation for combining the spectra of the input influence of the network and its response. Based on the analysis of the proposed model, it is concluded that it is possible to reduce the number of neurons in the hidden layer and reduce the number of features for training the classifier 2020-06-19T13:30:20Z 2020-06-19T13:30:20Z 2020 Статья Vershkov, N.A., Kuchukov, V.A., Kuchukova, N.N., Babenko, M. The Wave Model of Artificial Neural Network // Proceedings of the 2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering, EIConRus 2020. - 2020. - Номер статьи 9039172. - Pages 542-547 http://hdl.handle.net/20.500.12258/12084 en Proceedings of the 2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering, EIConRus 2020 application/pdf Institute of Electrical and Electronics Engineers Inc. |
| institution |
СКФУ |
| collection |
Репозиторий |
| language |
English |
| topic |
Artificial neural network Correlation function Spectral analysis Data communication systems |
| spellingShingle |
Artificial neural network Correlation function Spectral analysis Data communication systems Vershkov, N. A. Вершков, Н. А. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Babenko, M. G. Бабенко, М. Г. The wave model of artificial neural network |
| description |
The article deals with the modeling of artificial neural networks as a system of information transmission. The analysis of the existing theoretical approaches to the optimization of the structure and training of neural networks is carried out. The proposed model is based on the commonality of decoding processes in information transmission systems and clustering processes in neural networks. In the process of building a neuron model, we consider the well-known problem of determining the bandwidth capacity of the communication channel with noise in the geometric terms and its adaptation to the problem of assigning the input signal to a certain cluster. A neuron is considered to be a universal network element capable of performing orthogonal transformations, filtering, and other transformations of the input sequence. The layer of neurons is considered as an information converter with a certain kernel for solving the problems of orthogonal transformation, matched filtering, and nonlinear transformation for combining the spectra of the input influence of the network and its response. Based on the analysis of the proposed model, it is concluded that it is possible to reduce the number of neurons in the hidden layer and reduce the number of features for training the classifier |
| format |
Статья |
| author |
Vershkov, N. A. Вершков, Н. А. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Babenko, M. G. Бабенко, М. Г. |
| author_facet |
Vershkov, N. A. Вершков, Н. А. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Babenko, M. G. Бабенко, М. Г. |
| author_sort |
Vershkov, N. A. |
| title |
The wave model of artificial neural network |
| title_short |
The wave model of artificial neural network |
| title_full |
The wave model of artificial neural network |
| title_fullStr |
The wave model of artificial neural network |
| title_full_unstemmed |
The wave model of artificial neural network |
| title_sort |
wave model of artificial neural network |
| publisher |
Institute of Electrical and Electronics Engineers Inc. |
| publishDate |
2020 |
| url |
https://dspace.ncfu.ru/handle/20.500.12258/12084 |
| work_keys_str_mv |
AT vershkovna thewavemodelofartificialneuralnetwork AT verškovna thewavemodelofartificialneuralnetwork AT kuchukovva thewavemodelofartificialneuralnetwork AT kučukovva thewavemodelofartificialneuralnetwork AT kuchukovann thewavemodelofartificialneuralnetwork AT kučukovann thewavemodelofartificialneuralnetwork AT babenkomg thewavemodelofartificialneuralnetwork AT babenkomg thewavemodelofartificialneuralnetwork AT vershkovna wavemodelofartificialneuralnetwork AT verškovna wavemodelofartificialneuralnetwork AT kuchukovva wavemodelofartificialneuralnetwork AT kučukovva wavemodelofartificialneuralnetwork AT kuchukovann wavemodelofartificialneuralnetwork AT kučukovann wavemodelofartificialneuralnetwork AT babenkomg wavemodelofartificialneuralnetwork AT babenkomg wavemodelofartificialneuralnetwork |
| _version_ |
1760599345213734912 |