Search
Browsing by Author "Golovko, Vladimir"
Now showing items 115 of 15

A New Technique for Restricted Boltzmann Machine Learning
Golovko, Vladimir; Kroshchanka, Aliaksandr; Turchenko, Volodymyr; Jankowski, Stanislaw; Treadwell, Douglas (Information Science Warsaw University of Technology, 2015)Over the last decade, deep belief neural networks have been a hot topic in machine learning. Such networks can perform a deep hierarchical representation of input data. The first layer can extract lowlevel features, the second layer can extract highlevel features and so on. In general, deep belief ...20231101

A Steganographic Method Using Learning Vector Quantization
Gorbashkо, Larisa; Golovko, Vladimir (BSTU, 2006)The new technique for embedding image data is presented. The message is subjects to vector quantizer by neural network. The modified data is inserted into the coiner in the wavelet transform domain. The vector quantization enables to increase the capacity of embedded data. The experimental results ...20231129

Behavior Patterns of adaptive MultiJoined Robot learned by MultiAgent Influence Reinforcement Learning
Kabysh, Anton; Golovko, Vladimir; Mikhniayeu, Andrei; Rubanau, Uladzimir; Lipnikas, Arunas (BSUIR, 2011)This paper describes behavior patterns produced by MultiJoined Robot learned via Influence Reinforcement learning. This learning technique used for distributed, adaptive and selforganizing control in multiagent system. This technique is quite simple and uses agent’s influences to estimate learning ...20231023

Computing of Lyapunov Exponents Techniques Using Neural Networks
Golovko, Vladimir; Savitsky, Yury (BSUIR, 2003)The authors examine neural network techniques for computing of Lyapunov spectrum using observations from unknown dynamical system. Such an approach is based on applying of multilayer perceptron (MLP) for forecasting the next state of dynamical system from the previous one. It allows for evaluating the ...20231117

Convergence and integration of artificial neural networks with knowledge bases in nextgeneration intelligent computer systems
Kovalev, Mikhail; Kroshchanka, Aliaksandr; Golovko, Vladimir (БГУИР, 2022)In the article, an approach to the integration and convergence of artificial neural networks with knowledge bases in nextgeneration intelligent computer systems through the representation and interpretation of artificial neural networks in a knowledge base is considered. The syntax, denotational, and ...20231102

Deep Convolutional Neural Network for Detection of Solar Panels
Golovko, Vladimir; Kroshchanka, Alexander; Mikhno, Egor; Komar, Myroslav; Sachenko, Anatoliy (Springer, 2020)The article describes a method for detecting solar panels in satellite imagery. Due to the growing popularity of this technology, problems associated with themaintenance of solar panels are also becoming relevant.Many service companies are interested in obtaining information about potential customers. ...20231101

Evolution of detectors in neural network immune system for pattern recognition
Bezobrazov, Sergei; Golovko, Vladimir (БГУ, 2011)In this paper we present the basic principles of the evolution of detectors in intelligent system for pattern recognition, such as malicious code detection. This system based on integration of both Al methods: artificial neural networks and artificial immune systems. The goal of the evolution is ...20231120

Neural Network Model for Transient Ischemic Attacks Diagnostics
Golovko, Vladimir; Apanel, Elena; Mastykin, Alexander; Vaitsekhovich, Henadzi; Evstigneev, Victor (BSUIR, 2011)In this paper the neural network model for transient ischemic attacks recognition have been addressed. The proposed approach is based on integration of the NPCA neural network and multilayer perceptron. The dataset from clinic have been used for experiments performing. Combining two different neural ...20231120

Neural Network Techniques for Intrusion Detection
Golovko, Vladimir; Vaitsekhovich, Leanid (BSTU, 2006)This paper presents the neural network approaches for building of intrusion detection system (IDS). Existing intrusion detection approaches have same limitations, namely low detection time and recognition accuracy. In order to overcome these limitations we propose several neural network systems for ...20231129

Neural Networks for Chaotic Time Series Forecasting
Golovko, Vladimir; Savitsky, Yury (BSUIR, 2001)This paper examines neural network in order to predict behavior o f chaotic systems. The prediction is performed both on the level o f emergent structures and on the level o f individual data points. The network is tested using the Henon and Lorenz chaotic time series. The results o f experiments and ...20231116

Neural networks in transient ischemic attacks diagnostics
Golovko, Vladimir; Apanel, Elena; Mastykin, Alexander; Vaitsekhovich, Henadzi (БГУ, 2011)In this paper the neural network model for transient ischemic attacks recognition have been addressed. The proposed approach is based on integration of the NPCA neural network and multilayer perceptron. The dataset from clinic have been used for experiments performing. Combining two different neural ...20231120

Some approaches to line detection on a task of linefollowing
Kaliukhovich, Dzmitry; Golovko, Vladimir; Paczynski, Andreas (БрГТУ, 2007)Kaliukhovich, D. Some approaches to line detection on a task of linefollowing / D. Kaliukhovich, V. Golovko, A. Paczynski // Современные проблемы математики и вычислительной техники : материалы V Республиканской научной конференции молодых ученых и студентов, Брест, 28–30 ноября 2007 года / Министерство ...20200302

Some Aspects of Chaotic Time Series Analysis
Golovko, Vladimir; Savitsky, Yury; Maniakov, Nikolaj; Rubanov, Vladimir (BSUIR, 2001)We address two aspects in chaotic time series analysis, namely the definition of embedding parameters and the largest Lyapunov exponent. It is necessary for performing state space reconstruction and identification of chaotic behavior. For the first aspect, we examine the mutual information for ...20231116

The nature of unsupervised learning in deep neural networks: A new understanding and novel approach
Golovko, Vladimir; Kroshchanka, Aliaksandr; Treadwell, Douglas (Springer, 2016)Over the last decade, the deep neural networks are a hot topic in machine learning. It is breakthrough technology in processing images, video, speech, text and audio. Deep neural network permits us to overcome some limitations of a shallow neural network due to its deep architecture. In this paper we ...20231101

Training of the recurrent neural networks for prediction
Savitsky, Jury; Golovko, Vladimir (BSUIR, 1999)In this paper the technique of creation of effective methods of training recurrent neural network for prediction problems are discussed. The various functions of activation of neural units are considered. The adaptive algorithms of training of neural networks with varied functions of activation of ...20231115