Open AccessRobust training of neural network via minimizing robust estimates of the average of loss functions
Author(s) -
З. М. Шибзухов,
М. А. Казаков,
Д. П. Димитриченко
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1203/1/012074
Subject(s) - empirical risk minimization , outlier , quantile , minification , artificial neural network , estimator , computer science , differentiable function , robustness (evolution) , mathematics , algorithm , artificial intelligence , mathematical optimization , statistics , mathematical analysis , biochemistry , chemistry , gene