METHODS FOR INCREASING THE CLASSIFICATION ACCURACY BASED ON MODIFICATIONS OF THE BASIC ARCHITECTURE OF CONVOLUTIONAL NEURAL NETWORKS

METHODS FOR INCREASING THE CLASSIFICATION ACCURACY BASED ON MODIFICATIONS OF THE BASIC ARCHITECTURE OF CONVOLUTIONAL NEURAL NETWORKS

Object of research: basic architectures of deep learning neural networks. Investigated problem: insufficient accuracy of solving the classification problem based on the basic architectures of deep learning neural networks. An increase in accuracy requires a significant complication of the archite...

Full description

Bibliographic Details
Main Authors: Svitlana Shapovalova, Yurii Moskalenko
Format: Article
Language:English
Published: PC Technology Center 2020-12-01
Series:ScienceRise
Subjects:
classification
convolutional neural network
resnet
efficientnet
deep neural network
deep learning
Online Access:http://journal.eu-jr.eu/sciencerise/article/view/1573

Internet

http://journal.eu-jr.eu/sciencerise/article/view/1573

Similar Items