Абай атындағы Қазақ ұлттық педагогикалық университетінің Хабаршысы. Физика-математика ғылымдары сериясы, 2021, т. 69, № 1, с. 378-383
RECOGNITION OF THE TEXT BY MEANS OF DEEP LEARNING
Аннотация · Abstract
Using neural networks, various variations of the classification of objects can be performed. Neural networks are usedin many areas of recognition. A big area in this area is text recognition. The paper considers the optimal way to build anetwork for text recognition, the use of optimal methods for activation functions, and optimizers. Also, the article checkedthe correctness of text recognition with different optimization methods.This article is devoted to the analysis of convolutional neural networks. In the article, a convolutional neural networkmodel will be trained with a teacher. Teaching with a teacher is a type of training for neural networks in which youprovide the input data and the desired result, that is, the student looking at the input data will understand that you need tostrive for the result that was provided to him.
Сведения · Details
- Журнал · Journal Абай атындағы Қазақ ұлттық педагогикалық университетінің Хабаршысы. Физика-математика ғылымдары сериясы
- Язык · Language английский
- Цитирования (Crossref) · Citations 0