Optimization of computational complexity of an artificial neural network
The article deals with the modelling of Artificial Neural Networks as an information transmission system to optimize their computational complexity. The analysis of existing theoretical approaches to optimizing the structure and training of neural networks is carried out. In the process of construct...
में बचाया:
| मुख्य लेखकों: | , , , , , , , , , |
|---|---|
| स्वरूप: | Статья |
| भाषा: | English |
| प्रकाशित: |
CEUR-WS
2021
|
| विषय: | |
| ऑनलाइन पहुंच: | https://dspace.ncfu.ru/handle/20.500.12258/18054 |
| टैग : |
टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
|
| id |
ir-20.500.12258-18054 |
|---|---|
| record_format |
dspace |
| spelling |
ir-20.500.12258-180542021-09-01T09:20:38Z Optimization of computational complexity of an artificial neural network Vershkov, N. A. Вершков, Н. А. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Kucherov, N. N. Кучеров, Н. Н. Shiriaev, E. M. Ширяев, Е. М. Mathematical transformations Network layers Complex networks Computational complexity Control systems Information filtering Multilayer neural networks The article deals with the modelling of Artificial Neural Networks as an information transmission system to optimize their computational complexity. The analysis of existing theoretical approaches to optimizing the structure and training of neural networks is carried out. In the process of constructing the model, the well-known problem of isolating a deterministic signal on the background of noise and adapting it to solving the problem of assigning an input implementation to a certain cluster is considered. A layer of neurons is considered as an information transformer with a kernel for solving a certain class of problems: orthogonal transformation, matched filtering, and nonlinear transformation for recognizing the input implementation with a given accuracy. Based on the analysis of the proposed model, it is concluded that it is possible to reduce the number of neurons in the layers of neural network and to reduce the number of features for training the classifier 2021-09-01T09:18:32Z 2021-09-01T09:18:32Z 2021 Статья Vershkov N. А., Kuchukov V. A., Kuchukova N. N., Kucherov N. N., Shiriaev E. M. Optimization of computational complexity of an artificial neural network // CEUR Workshop Proceedings. - 2021. - Том 2913. - Стр. 220 - 226 http://hdl.handle.net/20.500.12258/18054 en CEUR Workshop Proceedings application/pdf CEUR-WS |
| institution |
СКФУ |
| collection |
Репозиторий |
| language |
English |
| topic |
Mathematical transformations Network layers Complex networks Computational complexity Control systems Information filtering Multilayer neural networks |
| spellingShingle |
Mathematical transformations Network layers Complex networks Computational complexity Control systems Information filtering Multilayer neural networks Vershkov, N. A. Вершков, Н. А. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Kucherov, N. N. Кучеров, Н. Н. Shiriaev, E. M. Ширяев, Е. М. Optimization of computational complexity of an artificial neural network |
| description |
The article deals with the modelling of Artificial Neural Networks as an information transmission system to optimize their computational complexity. The analysis of existing theoretical approaches to optimizing the structure and training of neural networks is carried out. In the process of constructing the model, the well-known problem of isolating a deterministic signal on the background of noise and adapting it to solving the problem of assigning an input implementation to a certain cluster is considered. A layer of neurons is considered as an information transformer with a kernel for solving a certain class of problems: orthogonal transformation, matched filtering, and nonlinear transformation for recognizing the input implementation with a given accuracy. Based on the analysis of the proposed model, it is concluded that it is possible to reduce the number of neurons in the layers of neural network and to 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. Kucherov, N. N. Кучеров, Н. Н. Shiriaev, E. M. Ширяев, Е. М. |
| author_facet |
Vershkov, N. A. Вершков, Н. А. Kuchukov, V. A. Кучуков, В. А. Kuchukova, N. N. Кучукова, Н. Н. Kucherov, N. N. Кучеров, Н. Н. Shiriaev, E. M. Ширяев, Е. М. |
| author_sort |
Vershkov, N. A. |
| title |
Optimization of computational complexity of an artificial neural network |
| title_short |
Optimization of computational complexity of an artificial neural network |
| title_full |
Optimization of computational complexity of an artificial neural network |
| title_fullStr |
Optimization of computational complexity of an artificial neural network |
| title_full_unstemmed |
Optimization of computational complexity of an artificial neural network |
| title_sort |
optimization of computational complexity of an artificial neural network |
| publisher |
CEUR-WS |
| publishDate |
2021 |
| url |
https://dspace.ncfu.ru/handle/20.500.12258/18054 |
| work_keys_str_mv |
AT vershkovna optimizationofcomputationalcomplexityofanartificialneuralnetwork AT verškovna optimizationofcomputationalcomplexityofanartificialneuralnetwork AT kuchukovva optimizationofcomputationalcomplexityofanartificialneuralnetwork AT kučukovva optimizationofcomputationalcomplexityofanartificialneuralnetwork AT kuchukovann optimizationofcomputationalcomplexityofanartificialneuralnetwork AT kučukovann optimizationofcomputationalcomplexityofanartificialneuralnetwork AT kucherovnn optimizationofcomputationalcomplexityofanartificialneuralnetwork AT kučerovnn optimizationofcomputationalcomplexityofanartificialneuralnetwork AT shiriaevem optimizationofcomputationalcomplexityofanartificialneuralnetwork AT širâevem optimizationofcomputationalcomplexityofanartificialneuralnetwork |
| _version_ |
1760601856065667072 |