ПРОЕКТИРОВАНИЕ НЕЙРОННОЙ СЕТИ НА ПРИМЕРЕ РАСПОЗНАВАНИЯ РУКОПИСНЫХ ЦИФР
Нейронные сети
Published:
2023-03-31Section:
СтатьиArticle language:
RussianKeywords:
neural network, convolutional neural network, convolution, handwritten digit recognition, gradient descent method, MNIST database, PythonAbstract
This article is devoted to the implementation of an algorithm for recognizing handwritten digits using neural networks. Definition of a full-fledged neural network in Keras on a real example of handwritten digit recognition. Improving a full-fledged neural network in Keras by adding convolutional layers. An open database of MNIST handwritten digit images is considered as a test sample. The resulting model can be successfully used to solve problems of image classification and image recognition.
Тезекпаева, Ш., & Бакланова, О. (2023). ПРОЕКТИРОВАНИЕ НЕЙРОННОЙ СЕТИ НА ПРИМЕРЕ РАСПОЗНАВАНИЯ РУКОПИСНЫХ ЦИФР: Нейронные сети. Вестник ВКТУ, (1), 134–147. Retrieved from https://vestnik.ektu.kz/index.php/vestnik/article/view/296
Most read articles by the same author(s)
- Ольга Бакланова, APPLICATION OF THE NAIVE BAYES METHOD IN SOLVING THE SPAM FILTERING PROBLEM , Вестник ВКТУ: No. 2 (2024): "Вестник ВКТУ им.Д.Серикбаева"