Self-learning system and methods of selection of weight coefficients of neural network
D. KhalilovFergana branch of the Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Fergana, UzbekistanSevarakhon BozorovaFergana branch of the Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Fergana, UzbekistanSardorbek KhonturaevFergana branch of the Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Fergana, UzbekistanAbdumalik KhoitkulovFergana branch of the Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Fergana, UzbekistanDildorakhon SotvoldievaFergana branch of the Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Fergana, UzbekistanSherzod ToshmatovFergana branch of the Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Fergana, Uzbekistan
ABI
Аннотация
The present work is devoted to the problems of determining the parameters of neural networks. The methodology, algorithm and solution paths of finding the gradient descent, one of the main parameters in a neural network during machine learning, are presented. It is very important to minimize the error of finding the weight parameters of the neuron.
Перевод пока недоступен