ARTIFICIAL INTELLIGENCE AND DECISION MAKING
A METHOD FOR TRAINING AN INTELLIGENT AGENT USING DOUBLE DQN NETWORKS, WAYPOINTS AND REWARD FUNCTION
Volume 9, Issue №3, 2024
The problems of increasing the control efficiency of autonomous vehicles are considered. The problem of reducing the required computational resources for the intelligent vehicle control module is highlighted. ...
APPROACH TO VECTORIZATION OF DRAWINGS OF DESIGN DOCUMENTATION ON PAPER
Volume 9, Issue №3, 2024
The work proposes a solution to the problem of vectorization and machine interpretation of drawings of design documentation on paper, which provides the ability to automate the transfer ...
COMPARATIVE ANALYSIS OF DEEP LEARNING ALGORITHMS WITH REINFORCEMENT DDPG, PPO AND SAC FOR UNMANNED CAR CONTROL IN CARLA SIMULATOR
Volume 9, Issue №2, 2024
This paper presents a comparative analysis of three advanced deep reinforcement learning algorithms: Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) implemented in ...
ABOUT THE USE OF MACHINE LEARNING IN MODELING BUSINESS PROCESSES
Volume 9, Issue №2, 2024
In a highly competitive environment, as well as the activation of the domestic production market, enterprises need to quickly adapt to modern conditions. There is an obvious increase ...
THE USE OF GENERATIVE-ADVERSARIAL NEURAL NETWORKS FOR IMAGE GENERATION
Volume 9, Issue №1, 2024
This article discusses the topic of image generation using neural networks. Thanks to the development of deeper learning and artificial intelligence, neural networks have become a powerful tool ...
IMAGE SEGMENTATION FOR THE TASK OF DIAGNOSING FLAT-VALGUS DEFORMITY OF THE FEET
Volume 9, Issue №1, 2024
Flat-valgus deformity of the foot is a common condition that can lead to various health problems such as pain syndromes and curvature of the spine. For effective diagnosis ...
COMPARISON OF THE EFFICIENCY OF MACHINE LEARNING ALGORITHMS BY THE EXAMPLE OF FORECASTING THE AVERAGE ELECTRICITY CONSUMPTION OF INTEGRATED CONSUMER METERING DEVICES
Volume 9, Issue №1, 2024
Finding and reducing electricity losses is one of the key activities of network organizations to improve financial results. Forecasting based on a large number of criteria ...
APPLICATION OF MODERN DATA COLLECTION TECHNOLOGIES AND MACHINE LEARNING METHODS FOR FACE RECOGNITION
Volume 9, Issue №1, 2024
The article presents a comprehensive approach to the development and optimization of a neural network model for effective face recognition in a dynamic environment. In particular, the neural ...
SYSTEM-OBJECT CLASSIFICATION ANALYSIS OF THE SUBJECT DOMAIN
Volume 8, Issue №4, 2023
The article discusses the urgent task of improving the classification procedure in connection with its numerous shortcomings. To solve the problem, a systemic (system-object) approach to the procedure for ...
INFORMATION AND ANALYTICAL TECHNOLOGY OF THE FUTURE - INTERNET OF THINGS (IOT)
Volume 8, Issue №4, 2023
The work provides a brief overview of promising areas for using Internet of Things (IoT) technology. The author provides a brief analysis of the dynamics of the technology market, ...
DESIGN OF RECURRENT NEURAL NETWORKS FOR CLASSIFICATION OF AGE DIFFERENCES IN THE FUNCTIONING OF THE SYMBOLIC SYSTEM OF QUANTITY ASSESSMENT
Volume 8, Issue №4, 2023
The article presents the result of the development and training of 4 recurrent neural network architectures to solve the problem of classifying age-related differences in the functioning of the ...
DEVELOPMENT OF MACHINE LEARNING METHODS AND A LIBRARY OF INTERPRETABLE PREDICTIVE MODELING OF HUMAN BEHAVIOR DURING HIS ONLINE PROFILING
Volume 8, Issue №4, 2023
The study of individual psychological characteristics of people is important in the areas of education, management and administration, ensuring the safety of individuals and communities. There are various tools ...
CLASSIFICATION OF SPEECH DATA BY EMOTIONAL BACKGROUND
Volume 8, Issue №3, 2023
In this paper, the algorithm of classification of speech data by emotional background, developed by the authors, is considered. In particular, it describes a neural network created to ...
ESTIMATION OF PROBABILISTIC-TEMPORAL CHARACTERISTICS OF HUMAN-MACHINE DIALOGUE
Volume 8, Issue №3, 2023
The paper is devoted to the evaluation of the probabilistic-temporal characteristics of the human-machine dialogue. The authors conducted a number of experiments to study the characteristics of the ...
NOSQL TECHNOLOGY: TECHNICAL FEATURES, DEVELOPMENT PROSPECTS AND COMPARATIVE ADVANTAGES OVER SQL
Volume 8, Issue №3, 2023
This review article examines the concepts, technical features, and future developments of NoSQL technology, highlighting its advantages over conventional SQL databases. NoSQL databases have gained attention due to ...
INTELLECTUAL ANALYSIS OF SCIENTOMETRIC INDICATORS OF RUSSIAN COMPUTER SCIENCE JOURNALS
Volume 8, Issue №3, 2023
The article discusses issues related to forecasting scientometric indicators and clustering Russian scientific journals in the field of computer science with the aim of evaluating the current state ...
TO THE QUESTION OF APPLICATION OF SYSTEM-OBJECT SIMULATION OF ORGANIZATIONAL AND BUSINESS PROCESSES
Volume 8, Issue №2, 2023
The implementation of simulation modeling of management processes is one of the most effective methods of support. The purpose of this article is defined in the need to ...
THE METHOD OF IDENTIFYING INDIRECT SIGNS OF CORRUPTION ACTS BASED ON VIDEO RECORDINGS OF SPEECHES OF CIVIL SERVANTS
Volume 8, Issue №2, 2023
At the moment, the problem of countering corruption in the field of public service still does not lose its relevance. It is assumed that when committing acts of ...
PROTECTION AGAINST ADVERSARIAL ATTACKS ON AUDIO AND IMAGES IN ARTIFICIAL INTELLIGENCE MODELS USING THE SGEC METHOD
Volume 8, Issue №2, 2023
In the modern world, the use of artificial intelligence (AI) is increasingly facing the risk of adversarial attacks on audio and images. This article explores this issue and ...
COMPARISON OF EFFICIENCY OF DIFFERENT METHODS OF TRAINING NEURAL NETWORKS
Volume 8, Issue №1, 2023
The paper considers several approaches to training multilayer fully connected neural networks. In particular, the authors have developed an artificial neural network, the purpose of which is to ...
Page 1 of 2
|
Next
