|
This article is cited in 16 scientific papers (total in 16 papers)
NUMERICAL METHODS AND DATA ANALYSIS
Structure-functional analysis and synthesis of deep convolutional neural networks
Yu. V. Vizilter, V. S. Gorbatcevich, S. Yu. Zheltov Federal State Unitary Enterprise “State Research Institute of Aviation Systems” (FGUP “GosNIIAS”), Moscow, Russia
Abstract:
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.
Keywords:
deep neural networks, machine learning, data structures.
Received: 07.03.2019 Accepted: 27.06.2019
Citation:
Yu. V. Vizilter, V. S. Gorbatcevich, S. Yu. Zheltov, “Structure-functional analysis and synthesis of deep convolutional neural networks”, Computer Optics, 43:5 (2019), 886–900
Linking options:
https://www.mathnet.ru/eng/co714 https://www.mathnet.ru/eng/co/v43/i5/p886
|
Statistics & downloads: |
Abstract page: | 319 | Full-text PDF : | 121 | References: | 27 |
|