Structure-functional analysis and synthesis of deep convolutional neural networks
| Autor: | Sergey Yu. Zheltov, V. S. Gorbatsevich, Yu. V. Vizilter |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Structure (category theory) 020207 software engineering Pattern recognition 02 engineering and technology Convolutional neural network lcsh:Q350-390 Atomic and Molecular Physics and Optics Computer Science Applications data structures machine learning deep neural networks 020204 information systems 0202 electrical engineering electronic engineering information engineering lcsh:Information theory lcsh:QC350-467 Artificial intelligence Electrical and Electronic Engineering business Functional analysis (psychology) lcsh:Optics. Light |
| Zdroj: | Компьютерная оптика, Vol 43, Iss 5, Pp 886-900 (2019) |
| ISSN: | 2412-6179 0134-2452 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|