CONSTRUCTION OF NEURAL ARCHITECTURES WITH DESIRED BEHAVIOUR UNDER GEOMETRIC TRANSFORMATIONS OF THE INPUT
Journal of Numerical and Applied Mathematics · 2020
DOI: 10.17721/2706-9699.2020.1.03 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Numerical and Applied Mathematics, 2020. Verfasst von V. V. Dudar und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 18 Literaturangaben.
Abstract (Originalsprache)
We present a general method for analysis of convolutional layers under geometric transformations of the input that are linear with respect to pixel values. We also describe the algorithm for finding all possible types of behaviours of the output of convolutional layers under geometric transformations of the input. We also present a general method for construction of convolutional architectures with desired behaviour under geometric transformations of the input.
Zitieren
APA
Dudar, V. V., & Semenov, V. V. (2020). CONSTRUCTION OF NEURAL ARCHITECTURES WITH DESIRED BEHAVIOUR UNDER GEOMETRIC TRANSFORMATIONS OF THE INPUT. Journal of Numerical and Applied Mathematics. https://doi.org/10.17721/2706-9699.2020.1.03
Vancouver
Dudar VV, Semenov VV. CONSTRUCTION OF NEURAL ARCHITECTURES WITH DESIRED BEHAVIOUR UNDER GEOMETRIC TRANSFORMATIONS OF THE INPUT. Journal of Numerical and Applied Mathematics. 2020. doi:10.17721/2706-9699.2020.1.03
BibTeX
@article{Dudar2020,
author = {Dudar, V. V. and Semenov, V. V.},
title = {CONSTRUCTION OF NEURAL ARCHITECTURES WITH DESIRED BEHAVIOUR UNDER GEOMETRIC TRANSFORMATIONS OF THE INPUT},
journal = {Journal of Numerical and Applied Mathematics},
year = {2020},
doi = {10.17721/2706-9699.2020.1.03}
}
EUVIMED