Recognition of the MNIST dataset with defective rows Full article
| Conference |
15th International Scientific and Technical Conference: Applied Mechanics and Systems Dynamics 09-11 Nov 2021 , Омск |
||||
|---|---|---|---|---|---|
| Journal |
Journal of Physics: Conference Series
ISSN: 1742-6588 , E-ISSN: 1742-6596 |
||||
| Output data | Year: 2022, Volume: 2182, Number: 1, Article number : 012031, Pages count : DOI: 10.1088/1742-6596/2182/1/012031 | ||||
| Authors |
|
||||
| Affiliations |
|
Funding (1)
| 1 | Омский филиал ФГБУН «Институт математики им. С.Л. Соболева СО РАН». | FWNF-2022-0003 |
Abstract:
One of the well-known classification problems in machine learning is the problem of recognizing handwritten numbers. This task is solved, since there are different neural networks that determine with fairly high accuracy which number is shown in the picture. In this paper, we will consider the recognition of handwritten digits subjected to certain deformations. © Published under licence by IOP Publishing Ltd.
Cite:
Shevlyakov A.N.
, Berezin A.A.
Recognition of the MNIST dataset with defective rows
Journal of Physics: Conference Series. 2022. V.2182. N1. 012031 . DOI: 10.1088/1742-6596/2182/1/012031 Scopus РИНЦ OpenAlex
Recognition of the MNIST dataset with defective rows
Journal of Physics: Conference Series. 2022. V.2182. N1. 012031 . DOI: 10.1088/1742-6596/2182/1/012031 Scopus РИНЦ OpenAlex
Identifiers:
| Scopus: | 2-s2.0-85127645344 |
| Elibrary: | 48426190 |
| OpenAlex: | W4221011221 |