Structure-functional analysis and synthesis of deep convolutional neural networks
| Title: | Structure-functional analysis and synthesis of deep convolutional neural networks |
|---|---|
| Authors: | Yuri Vizilter, Vladimir Gorbatsevich, Sergey Zheltov |
| Source: | Компьютерная оптика, Vol 43, Iss 5, Pp 886-900 (2019) |
| Publisher Information: | Samara National Research University, 2019. |
| Publication Year: | 2019 |
| Collection: | LCC:Information theory LCC:Optics. Light |
| Subject Terms: | deep neural networks, machine learning, data structures, Information theory, Q350-390, Optics. Light, QC350-467 |
| More Details: | A general approach to a structure-functional analysis and synthesis (SFAS) of deep neural networks (CNN). The new approach allows to define regularly: from which structure-functional elements (SFE) CNNs can be constructed; what are required mathematical properties of an SFE; which combinations of SFEs are valid; what are the possible ways of development and training of deep networks for analysis and recognition of an irregular, heterogeneous data or a data with a complex structure (such as irregular arrays, data of various shapes of various origin, trees, skeletons, graph structures, 2D, 3D, and ND point clouds, triangulated surfaces, analytical data descriptions, etc.) The required set of SFE was defined. Techniques were proposed that solve the problem of structure-functional analysis and synthesis of a CNN using SFEs and rules for their combination. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English Russian |
| ISSN: | 2412-6179 0134-2452 |
| Relation: | http://computeroptics.ru/KO/PDF/KO43-5/430521.pdf; https://doaj.org/toc/0134-2452; https://doaj.org/toc/2412-6179 |
| DOI: | 10.18287/2412-6179-2019-43-5-886-900 |
| Access URL: | https://doaj.org/article/7bf24ca22dc34758a900a8fadb9446e1 |
| Accession Number: | edsdoj.7bf24ca22dc34758a900a8fadb9446e1 |
| Database: | Directory of Open Access Journals |
| ISSN: | 24126179 01342452 |
|---|---|
| DOI: | 10.18287/2412-6179-2019-43-5-886-900 |
| Published in: | Компьютерная оптика |
| Language: | English Russian |