Parallel algorithm for calculating the learning processes of an artificial neural network
Hakimjon ZaynidinovTashkent university of Information technologies named after Muhammad al-Khwarizmi (TUIT), Tashkent, UzbekistanOybek MallayevTashkent university of Information technologies named after Muhammad al-Khwarizmi (TUIT), Tashkent, Uzbekistan
ABI
Abstract
Nowadays, the digital processing of graphic data is undergoing unprecedented changes. Recently, the use of artificial intelligence has become more and more important in all areas. In this article, an algorithm for parallelizing the learning processes of a neural network has been developed. The algorithm identifies an area of a person’s face from an image and performs parallel labor-intensive processes associated with training a neural network. Parallelization of the processes of organizing neural nodes (layers) is carried out in the Python programming language.
Topics
Identifiers
Citations and references
Metrics — AkademScholar · Coming soon