Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior
The article presents an approach to configuration of an artificial neural network architecture and a training set size. Configuration is based on parameter minimization with constraints specifying neural network model quality criteria. The algorithm of artificial neural network architecture and trai...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Institute of Computer Science
2015-04-01
|
| Series: | Компьютерные исследования и моделирование |
| Subjects: | |
| Online Access: | http://crm.ics.org.ru/uploads/crmissues/crm_2015_2/15704.pdf |
| _version_ | 1818458875159904256 |
|---|---|
| author | Aleksandr Georgievich Shumixin Anna Sergeevna Boyarshinova |
| author_facet | Aleksandr Georgievich Shumixin Anna Sergeevna Boyarshinova |
| author_sort | Aleksandr Georgievich Shumixin |
| collection | DOAJ |
| description | The article presents an approach to configuration of an artificial neural network architecture and a training set size. Configuration is based on parameter minimization with constraints specifying neural network model quality criteria. The algorithm of artificial neural network architecture and training set size configuration is applied to dynamic object artificial neural network approximation.Series of computational experiments were performed. The method is applicable to construction of dynamic object models based on non-linear autocorrelation neural networks. |
| first_indexed | 2024-12-14T23:05:24Z |
| format | Article |
| id | doaj.art-b0662905d96c49caa41be2117fbe51c5 |
| institution | Directory Open Access Journal |
| issn | 2076-7633 2077-6853 |
| language | Russian |
| last_indexed | 2024-12-14T23:05:24Z |
| publishDate | 2015-04-01 |
| publisher | Institute of Computer Science |
| record_format | Article |
| series | Компьютерные исследования и моделирование |
| spelling | doaj.art-b0662905d96c49caa41be2117fbe51c52022-12-21T22:44:20ZrusInstitute of Computer ScienceКомпьютерные исследования и моделирование2076-76332077-68532015-04-017224325110.20537/2076-7633-2015-7-2-243-2512260Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behaviorAleksandr Georgievich ShumixinAnna Sergeevna BoyarshinovaThe article presents an approach to configuration of an artificial neural network architecture and a training set size. Configuration is based on parameter minimization with constraints specifying neural network model quality criteria. The algorithm of artificial neural network architecture and training set size configuration is applied to dynamic object artificial neural network approximation.Series of computational experiments were performed. The method is applicable to construction of dynamic object models based on non-linear autocorrelation neural networks.http://crm.ics.org.ru/uploads/crmissues/crm_2015_2/15704.pdfdynamic object modeltraining setartificial neural networkarchitecturetrainingoptimization of artificial neural network architecture |
| spellingShingle | Aleksandr Georgievich Shumixin Anna Sergeevna Boyarshinova Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior Компьютерные исследования и моделирование dynamic object model training set artificial neural network architecture training optimization of artificial neural network architecture |
| title | Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior |
| title_full | Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior |
| title_fullStr | Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior |
| title_full_unstemmed | Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior |
| title_short | Algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior |
| title_sort | algorithm of artificial neural network architecture and training set size configuration within approximation of dynamic object behavior |
| topic | dynamic object model training set artificial neural network architecture training optimization of artificial neural network architecture |
| url | http://crm.ics.org.ru/uploads/crmissues/crm_2015_2/15704.pdf |
| work_keys_str_mv | AT aleksandrgeorgievichshumixin algorithmofartificialneuralnetworkarchitectureandtrainingsetsizeconfigurationwithinapproximationofdynamicobjectbehavior AT annasergeevnaboyarshinova algorithmofartificialneuralnetworkarchitectureandtrainingsetsizeconfigurationwithinapproximationofdynamicobjectbehavior |