Open AccessNeural Network Effectiveness Evaluation While the Intersection of Images in the Receptor Field
Author(s) -
Siranush Sargsyan,
Anna Hovakimyan
Publication year - 2021
Publication title -
wseas transactions on information science and applications
Language(s) - English
Resource type - Journals
eISSN - 2224-3402
pISSN - 1790-0832
DOI - 10.37394/23209.2020.17.21
Subject(s) - artificial neural network , probabilistic neural network , intersection (aeronautics) , field (mathematics) , computer science , artificial intelligence , time delay neural network , set (abstract data type) , probabilistic logic , perceptron , path (computing) , pattern recognition (psychology) , mathematics , geography , computer network , cartography , pure mathematics , programming language
The study and application of neural networks is one of the main areas in the field of artificial intelligence. The effectiveness of the neural network depends significantly on both its architecture and the structure of the training set. This paper proposes a probabilistic approach to evaluate the effectiveness of the neural network if the images intersect in the receptor field. A theorem and its corollaries are proved, which are consistent with the results obtained by a different path for a perceptron-type neural network.