MODERN EDUCATION AND DEVELOPMENT
Выпуск журнала №-26
Часть–6_ Май –2025
205
PROPERTIES OF CONVOLUTIONAL NEURAL NETWORKS.
Musaeva Nurjahon Aktamkhon kizi,
Karshi State Technical University,
Student of the Department of Telecommunication Technologies
Annotation. Convolutional neural networks are widely used in artificial
intelligence and machine learning in image analysis, natural language processing, and
other complex data processing. The main characteristics of CNNs are automatic
feature learning, extraction of important elements in images and data, invariance,
hierarchical feature detection, and efficient parameter sharing. This article provides
detailed information on the working principle of convolutional neural networks, their
layers (convolution, pooling, fully connected), as well as how they are used in real-
world problems.
Key words: Convolutional neural network, artificial intelligence, machine
learning areas, natural language processing, images and data, invariance,
hierarchical feature, neural network, layers, convolution, pooling, fully connected.
Аннотация. Сверточные нейронные сети широко используются в
искусственном интеллекте и машинном обучении при анализе изображений,
обработке естественного языка и другой сложной обработке данных.
Основными характеристиками CNN являются автоматическое обучение
признакам, извлечение важных элементов из изображений и данных,
инвариантность, иерархическое обнаружение признаков и эффективное
совместное использование параметров. В этой статье представлена подробная
информация о принципе работы сверточных нейронных сетей, их слоях
(свертка, объединение, полная связность), а также о том, как они
используются в реальных задачах.
Ключевые слова: Сверточная нейронная сеть, искусственный
интеллект, области машинного обучения, обработка естественного языка,
MODERN EDUCATION AND DEVELOPMENT
Выпуск журнала №-26
Часть–6_ Май –2025
206
изображения и данные, инвариантность, иерархический признак, нейронная
сеть, слои, свертка, объединение, полная связность.
In the fields of artificial intelligence and machine learning, convolutional
neural networks (CNNs) play a very important role. They are mainly used in image
processing and classification, but are now also used in natural language processing,
voice data, and many other areas. CNNs differ from other neural networks in their
structure and operating principle, as they are multilayered and adapted for automatic
feature learning. This article analyzes the main characteristics of convolutional neural
networks and their operating principles.
Basic concepts of convolutional neural networks. Convolutional neural
networks are a special type of artificial neural networks, the main purpose of which is
to automatically learn features from images or other data sets. CNNs often consist of
the following parts:
Convolutional Layers. The most important component of a CNN is the
convolutional layers. These layers divide the image into small parts and analyze each
part independently. Each convolution layer contains a small matrix called a "kernel" or
"filter" that operates on each pixel of the image. The purpose of the filter is to extract
important features in the image (such as edges, corners, structures, etc.).
Activation Function. After the convolution operation, the results are passed
through an activation function. The most commonly used activation function is ReLU
(Rectified Linear Unit), which activates a specific feature, and if it is negative, it is
equal to 0. The ReLU function helps reduce the uncertainty of the model and speed up
the calculation.
Pooling Layers. After the convolution layer, pooling layers are often used.
Pooling is mainly used to reduce the dimensions of the image, which reduces the
calculation time and is effective in training the model. Techniques such as max pooling
or average pooling help in extracting important features from an image. Max pooling,
for example, preserves the important features of an image by selecting the largest value
within a small portion of the image.
MODERN EDUCATION AND DEVELOPMENT
Выпуск журнала №-26
Часть–6_ Май –2025
207
Fully Connected Layers. At the end of a CNN, there are fully connected layers.
These layers connect each neuron to all neurons in the network and are used to make
final decisions. Their job is to transform the features extracted from the image into the
final classification or regression result.
Normalization. Techniques such as batch normalization are used for CNNs to
speed up learning and increase the generalization ability of the model. This technique
normalizes the data at each layer of the network, so that the learning process of the
network becomes more stable and efficient.
Features of Convolutional Neural Networks. Automatic feature learning. The
biggest feature of CNNs is that they can automatically learn features from images or
other data. This is useful, for example, in image classification, because the network
learns the specific features in the image, such as edges, colors, textures, and other
important elements. As a result, CNNs do not require much manual feature extraction,
and they are very effective in solving complex classification problems.
Invariance. CNNs are invariant to the dimensions, rotations, and stresses in
images or other data. For example, even if the same image is shown from different
angles, a CNN can still be highly accurate in identifying it. This increases the network's
generalization ability and provides flexibility to various changes.
Hierarchical feature learning. CNNs often have a multi-layer architecture, with
different features detected in each layer. The initial layers detect simple features (such
as edges and corners), while subsequent layers combine these features and learn more
complex features. This allows you to create a hierarchical structure, which is important
for object recognition in an image.
Dimensionality reduction. The use of pooling layers in a convolutional network
reduces the dimensions of the image, which increases computational efficiency.
Pooling is especially useful when working with large images, as it compresses the
information and allows the network to train more quickly and efficiently.
Sharing parameters between layers. In CNNs, convolutional layers share
parameters with each other through filters. This reduces the number of parameters in
MODERN EDUCATION AND DEVELOPMENT
Выпуск журнала №-26
Часть–6_ Май –2025
208
the model, making the network more efficient and faster. This feature makes CNNs
very suitable for working with large amounts of data.
Convolutional neural networks are widely used in the following areas:
Image recognition. CNNs are most commonly used in image classification and
recognition. They are used in image classification, face recognition, object detection,
and also in the analysis of medical images (such as X-ray and MRI images).
Video analysis. CNNs are also used in video data analysis. They are used to
detect objects in videos, analyze movements, and so on. For example, CNNs are used
in analyzing video streams from security cameras to detect moving objects or people.
Natural language processing. In recent years, CNNs have also been used in
natural language processing. They are used for tasks such as text classification, emotion
recognition, and machine translation.
Automated driving systems. CNNs are also used to create automated drivers in
changing environments. By analyzing the image of a car, they help to identify objects,
recognize obstacles, and determine the right path.
Convolutional neural networks play an important role in the fields of artificial
intelligence and machine learning. Their properties such as automatic feature learning,
invariance, and hierarchical feature detection make them effective in solving image
analysis, natural language processing, and other complex problems. CNNs are widely
used in various fields and are working as very effective and powerful tools in solving
real-world problems.
REFERENCES:
1.
Даминова Б. Э. и др. ОБРАБОТКА ВИДEОМАТEРИАЛОВ ПРИ
РАЗРАБОТКE ОБРАЗОВАТEЛЬНЫХ РEСУРСОВ //Экономика и социум. –
2024. – №. 2-2 (117). – С. 435-443.
2.
Daminova B. E. GAUSS AND ITERATION METHODS FOR SOLVING A
SYSTEM OF LINEAR ALGEBRAIC EQUATIONS //Экономика и социум. – 2024.
– №. 2 (117)-1. – С. 235-239.
3.
Daminova B. E., Oripova M. O. METHODS OF USING MODERN
METHODS BY TEACHERS OF MATHEMATICS AND INFORMATION
MODERN EDUCATION AND DEVELOPMENT
Выпуск журнала №-26
Часть–6_ Май –2025
209
TECHNOLOGIES IN THE CLASSROOM //Экономика и социум. – 2024. – №. 2
(117)-1. – С. 256-261.
4.
Daminova B. E. et al. USE OF ELECTRONIC EDUCATIONAL
RESOURCES IN THE PROCESS OF TEACHING A FOREIGN LANGUAGE
//Экономика и социум. – 2024. – №. 5-1 (120). – С. 230-232.
5.
Daminova B. E. et al. USING COMPUTER PRESENTATIONS IN
TEACHING FOREIGN LANGUAGES //Экономика и социум. – 2024. – №. 5-1
(120). – С. 211-215.
6.
Daminova B. E. et al. USING DIGITAL TECHNOLOGIES IN FOREIGN
LANGUAGE LESSONS //Экономика и социум. – 2024. – №. 5-1 (120). – С. 226-
229.
7.
Daminova B. E., Bozorova I. J., Jumayeva N. X. FORMATION OF TEXT
DATA PROCESSING SKILLS //Экономика и социум. – 2024. – №. 4-2 (119). – С.
110-119.
8.
Daminova B. E. et al. USE OF ONLINE ELECTRONIC DICTIONARIES IN
ENGLISH LANGUAGE LESSONS //Экономика и социум. – 2024. – №. 5-1 (120).
– С. 193-196.
9.
Daminova B. E. et al. ADVANTAGES OF USING MULTIMEDIA
RESOURCES IN ENGLISH LANGUAGE LESSONS //Экономика и социум. –
2024. – №. 5-1 (120). – С. 207-210.
10.
Daminova B. E. et al. SCIENTIFIC AND METHODOLOGICAL SUPPORT
OF EDUCATIONAL INFORMATION INTERACTION IN THE EDUCATIONAL
PROCESS BASED ON INTERACTIVE ELECTRONIC EDUCATIONAL
RESOURCES: USING THE EXAMPLE OF TEACHING ENGLISH //Экономика и
социум. – 2024. – №. 5-1 (120). – С. 233-236.
11.
Daminova B. E. et al. THE ROLE AND FEATURES OF THE USE OF
INFORMATION TECHNOLOGY IN TEACHING A FOREIGN LANGUAGE
//Экономика и социум. – 2024. – №. 5-1 (120). – С. 184-188.
MODERN EDUCATION AND DEVELOPMENT
Выпуск журнала №-26
Часть–6_ Май –2025
210
12.
Daminova B. E. et al. USING THE GOOGLE CLASSROOM WEB SERVICE
AND PREPARING INTERACTIVE PRESENTATIONS //Экономика и социум. –
2024. – №. 5-1 (120). – С. 216-225.
13.
Daminova B. E., Bozorova I. J., Jumayeva N. X. CREATION OF
ELECTRONIC LEARNING MATERIALS USING MICROSOFT WORD
PROGRAM //Экономика и социум. – 2024. – №. 4-2 (119). – С. 104-109.
14.
Daminova B. E. et al. APPLICATION OF MODERN INFORMATION AND
COMMUNICATION TECHNOLOGIES IN TEACHING ENGLISH //Экономика и
социум. – 2024. – №. 5-1 (120). – С. 197-201.
15.
Daminova B. E. et al. SOFTWARE TOOLS FOR CREATING MULTIMEDIA
RESOURCES IN TEACHING ENGLISH //Экономика и социум. – 2024. – №. 5-1
(120). – С. 202-206.
16.
Daminova B. E. et al. THE MAIN ADVANTAGES, PROBLEMS AND
DISADVANTAGES OF USING MULTIMEDIA IN TEACHING FOREIGN
LANGUAGES //Экономика и социум. – 2024. – №. 5-1 (120). – С. 189-192.
