Abstract: The paper discusses the theoretical aspects of the mathematical model of convolutional neural networks
as a means of classifying the information was not originally a graphic of origin. The description of this approach was
illustrated by the information classification of customs control, which involves the transformation of a set of vectors
multitype information graphics (pseudographic patterns).
Keywords: convolutional neural network, customs control, risk management
ACM Classification Keywords: I.5 PATTERN RECOGNITION – I.5.1 Models – Neural nets.
Link:
CONVOLUTION NETWORKS AS A METHOD OF REALISATION OF CUSTOMS
RISK-MANAGEMENT
Boris Moroz, Sergii Konovalenko
http://www.foibg.com/ijitk/ijitk-vol06/ijitk06-4-p05.pdf
Wiki
(1.00/10)
