Regularization of automatic training of Mahalanobis neurons for small samples of examples of the “Own” image
The paper considers the problem of regularization of automatic stable training of networks of artificial Mahalanobis neurons that simultaneously perform recognition of the “Own” image.
Main Authors: | Zolotareva T.A., Ivanov A.I., Selishchev O.V., Skudnev D.M. |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2020-01-01
|
Series: | E3S Web of Conferences |
Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/84/e3sconf_TPACEE2020_01024.pdf |
Similar Items
-
Optimized Mahalanobis–Taguchi System for High-Dimensional Small Sample Data Classification
by: Xinping Xiao, et al.
Published: (2020-01-01) -
Intelligent system of identification of local area network state
by: Voronin Ilya, et al.
Published: (2021-01-01) -
The distribution of the extreme Mahalanobis' distnace from the sample mean
by: Cuttle, Yvonne Germaine Marie Ghislaine
Published: (2012) -
Mahalanobis-Taguchi System for Symbolic Interval Data Based on Kernel Mahalanobis Distance
by: Zhipeng Chang, et al.
Published: (2020-01-01) -
Multi-criteria neural network estimation of correlation coefficients for processing small samples of biometric data
by: A.I. Ivanov, et al.
Published: (2021-03-01)