Поиск по всему репозиторию:

Conference materials by articles: Недавние поступления

Отображаемые элементы 1-20 из 39

    • Methods of Partial Logic 

      Prihozhy, A. (BPI, 1999)
      This paper presenls novel theoretical results obtained in the field of partial logie. New operations (including a very useful minimization operation), laws, and expansions are introduced. Traditional Boolean function representation forms for the completely specified functions are generalized for the ...

      2021-07-27

    • Determination of Features of the Dependence of Neuron Net Output Coordinates on Other Coordinates and Parameters of Neuron Net 

      Ptitchkin, V. (BPI, 1999)
      The paper presents the deduction of main relationships of back-propagation algorithm on the basis of approximation of the unknown dependence of the efficiency factor on neural net parameters by the linear part of Taylor series. Such an approach for deduction of known results is intended to relax the ...

      2021-07-27

    • Generalization of Ruspini's Likeness Relation in Cases of Subnormal Relations 

      Viattchenin, D. A. (BPI, 1999)
      The note deals in a preliminary way with the problem of a generalization of a likeness relation. Preliminary results are considered. Defmition of generalized likeness relation is proposed. Some preliminary conclusions are made.

      2021-07-27

    • New Approach of the Recurrent Neural Network Training 

      Golovko, V.; Savitsky, Y. (BPI, 1999)
      In this work the technique o f creation o f adapthre training algorithms for recurrent neural networks (RNN) is cortsidered. These algorithms have high convergence and accuracy on a comparison with traditional backpropagation. The original technique of calculation of an adaptive training step with use ...

      2021-07-27

    • The Training of Feed-Forward Neural Networks 

      Golovko, V.; Dunets, A.; Savitsky, Y. (BPI, 1999)
      The training of multilayer perceptron is generally a difficult task. Excessive training times and lack of convergence to an acceptable solution are frequently reported. This paper discribes new training methods of feedforward neural networks. In comparison with standard backpropagation algorithm it ...

      2021-07-27

    • Multi-Scale Image Analysis and Applications in Framework of the Intas 96-785 Project 

      Heijmans, H. J. A. M.; Kirichuk, V. S.; Kovalev, V. A.; Pauwels, E. J.; Petrou, M.; Tsurkov, V. I.; Tuzikov, А. V. (BPI, 1999)
      Multi-Scale Image Analysis and Applications in Framework of the Intas 96-785 Project / H. J. A. M. Heijmans [and etc.] // International Conference on Neural Networks and Artificial Intelligence ICNNAI’99 = Международная конференция по нейронным сетям и искусственному интеллекту ICNNAI’99 : Proceedings, ...

      2021-07-27

    • Decomposition Approach to Minimize a Class of Superposition of Recurrent Monotone Functions on a Set of Parameterized Paths in Digraph 

      Guschinsky, N.; Levin, G. (BPI, 1999)
      A problem of finding optimal parameterized path in digraph is considered. A parameterized path is a path each arc of which is assigned a parameter fforn a given set. A superposition of recurrent-monotone functions is accepted as an objective fimction where one of the functions is defined by using max ...

      2021-07-27

    • Neural Network Model of Associative Memory: To Visualize Solutions in Weight Space 

      Imada, A. (BPI, 1999)
      We apply some variants of evolutionary computations to the Hopfield model of associative memory. In the model, a number of patterns can be stored in the network as attractors if synaptic weights are determined appropriately. One of our goals of this study is to learn the number and distribution of ...

      2021-07-27

    • Synthesis of a Test Generator for a Built-ln Self-Test Scheme 

      Khomich , O. V.; Yarmolik, V. N. (BPI, 1999)
      This paper presents a new algorithm for the automated synthesis of pseudo-random test patterns generators for Built-ln Self Test schemes with a mixed testmode. The experimental resulls showan opportunity of using the given method on a design stage of circuits producing In this paper it is shown that ...

      2021-07-27

    • Computer Modeling the Excitonic Reflection and Photoluminescence Spectra of GaN Epitaxial Layers 

      Rakovich, Y.; Tarasjuk, N. P.; Gladyshchuk, A. A.; Lucenko, E. V.; Yablonskii, G. P.; Heuken, M.; Heime, K. (BPI, 1999)
      Photoluminescence (PL) and reflection excitonic spectra o f GaN single layer grown on sapphire substrate by MOVPE were modeled with aim to estimate a basie parameters o f free A- and B- excitons. The calculations were performed in the frame o f two-oscillator model for dielectric function e(E). Three ...

      2021-07-27

    • The Universal Contact Device for Monitoring Printed Circuit Cards 

      Shoot, V.; Prozherin, I. (BPI, 1999)
      Shoot, V. The Universal Contact Device for Monitoring Printed Circuit Cards / V. Shoot, I. Prozherin // International Conference on Neural Networks and Artificial Intelligence ICNNAI'99 = Международная конференция по нейронным сетям и искусственному интеллекту ICNNAI'99 : Proceedings, Brest, Belarus, ...

      2021-07-27

    • Program Improvement of Quality of the Images at 2D Acoustic Visualization 

      Акулич, Ярослав Антонович; Kostiuk, Dmitriy; Kudinov, N. V.; Kuzavko, Y. A. (BPI, 1999)
      The various program methods are offered (linear filtration, processing on special functions with an adjustable weights, color-coding) to improve the images quality at 2D acoustic visualization of solidstate products, which are illustrated on an example of researches of friction pair. Overlapping the ...

      2021-07-27

    • Architecture of Computer Vision Software System 

      Ivkin, A.; Doudkin, A.; Sadykhov, R. (BPI, 1999)
      The software o f the Computer vision systems is complicated. The authors discuss the principles of Computer vision systems organization and propose the architecture for such software system.

      2021-07-27

    • Application of Genetic Algorithms for Solutions of the Task Is Frequent – Territorial Plannings Group Radio Electronic Equipment 

      Kulaga, V. V.; Muravjev, S. A.; Spiridonov, S. V.; Telyatnikov, R. V. (BPI, 1999)
      One from the important problems, is a problem of limited frequencyТs number between radio electronic equipment's (REE) within large group. It is necessary that all REE may operate with specific correlation of signal-noise (interference) on boundaries of their service's zones, сon sideling of electromagnetic ...

      2021-07-27

    • Walsh Operators of Edge Detection for Gray-Scale Images 

      Machnev, A. G.; Selikhanovich, A. M. (BPI, 1999)
      Walsh operators are proposed that may be used in image processing for edge detection. These operators based on discrete two-dimensional Walsh functions of appropriate dimensionality. The algorithms of a calculation of operators and the algorithm of edge detection are represented.

      2021-07-27

    • Anomalies of Reflection of Acoustic Pulses from Boundary with Strong Dissipatiye Medium 

      Kostiuk, Dmitriy; Kuzavko, Y. A. (BPI, 1999)
      In given work the longitudinal acoustic waves reflection from boundary of a solid body with dissipative liquid theoretically is considered. The essential dependence of factor of signal reflection and its phase from factor of absorption of ultrasound in dissipative medium is shown. The experimental ...

      2021-07-27

    • Unsupervised Training Algorithm for Recirculation Neural Network 

      Golovko, V.; Gladyschuk, V. (BPI, 1999)
      Unsupemised learning is the great promise of the future. In such training the network is provided with inputs but not with desired outputs. Unsupemised learning is used for the principal component networks. This paper describes a nerw method for training of the recirculation networks. Such method is ...

      2021-07-27

    • The Application of Self-Organizing Neural Networks in Financial Market Analysis 

      Stankevicius, G. (BPI, 1999)
      The problem of comparison of different companies is facing, when analyzing company's performance in stock exchange market. Due to many different fmancial ratios and parameters sometimes it is almost impossible to decide which company is a leader or not. One of the ways to solve this problem is the use ...

      2021-07-27

    • Neuroelectronic Systems: Binding Neurons to Electric Circuits 

      Molchanov, P. G.; Denisov, A. A.; Martinovich, G. G.; Cherenkevich, S. N. (BPI, 1999)
      This paper is devoted to description of a new type of information system based on interaction of biological neurons and electronic components – neuroelectronic (NE) system. Main features and components, like neural network sensor, of NE are briefly put into consideration followed with an example of ...

      2021-07-27

    • Fuzzy Expert System for a Stock Trading Process 

      Simutis, R.; Stankevicius, G.; Veckys, A. (BPI, 1999)
      The goal of this study was to build and to evaluate a human skill based fuzzy expert system for a decision making support in stock trading process. Our focus was concentrated on Computer software that is capable to reproduce the knowledge from the skilled stock trader. Using classical technique and ...

      2021-07-27