Результаты поиска по 'training':
Найдено статей: 48
  1. Vostrikov D.D., Konin G.O., Lobanov A.V., Matyukhin V.V.
    Influence of the mantissa finiteness on the accuracy of gradient-free optimization methods
    Computer Research and Modeling, 2023, v. 15, no. 2, pp. 259-280

    Gradient-free optimization methods or zeroth-order methods are widely used in training neural networks, reinforcement learning, as well as in industrial tasks where only the values of a function at a point are available (working with non-analytical functions). In particular, the method of error back propagation in PyTorch works exactly on this principle. There is a well-known fact that computer calculations use heuristics of floating-point numbers, and because of this, the problem of finiteness of the mantissa arises.

    In this paper, firstly, we reviewed the most popular methods of gradient approximation: Finite forward/central difference (FFD/FCD), Forward/Central wise component (FWC/CWC), Forward/Central randomization on $l_2$ sphere (FSSG2/CFFG2); secondly, we described current theoretical representations of the noise introduced by the inaccuracy of calculating the function at a point: adversarial noise, random noise; thirdly, we conducted a series of experiments on frequently encountered classes of problems, such as quadratic problem, logistic regression, SVM, to try to determine whether the real nature of machine noise corresponds to the existing theory. It turned out that in reality (at least for those classes of problems that were considered in this paper), machine noise turned out to be something between adversarial noise and random, and therefore the current theory about the influence of the mantissa limb on the search for the optimum in gradient-free optimization problems requires some adjustment.

  2. Nebaba S.G., Markov N.G.
    Convolutional neural networks of YOLO family for mobile computer vision systems
    Computer Research and Modeling, 2024, v. 16, no. 3, pp. 615-631

    The work analyzes known classes of convolutional neural network models and studies selected from them promising models for detecting flying objects in images. Object detection here refers to the detection, localization in space and classification of flying objects. The work conducts a comprehensive study of selected promising convolutional neural network models in order to identify the most effective ones from them for creating mobile real-time computer vision systems. It is shown that the most suitable models for detecting flying objects in images, taking into account the formulated requirements for mobile real-time computer vision systems, are models of the YOLO family, and five models from this family should be considered: YOLOv4, YOLOv4-Tiny, YOLOv4-CSP, YOLOv7 and YOLOv7-Tiny. An appropriate dataset has been developed for training, validation and comprehensive research of these models. Each labeled image of the dataset includes from one to several flying objects of four classes: “bird”, “aircraft-type unmanned aerial vehicle”, “helicopter-type unmanned aerial vehicle”, and “unknown object” (objects in airspace not included in the first three classes). Research has shown that all convolutional neural network models exceed the specified threshold value by the speed of detecting objects in the image, however, only the YOLOv4-CSP and YOLOv7 models partially satisfy the requirements of the accuracy of detection of flying objects. It was shown that most difficult object class to detect is the “bird” class. At the same time, it was revealed that the most effective model is YOLOv7, the YOLOv4-CSP model is in second place. Both models are recommended for use as part of a mobile real-time computer vision system with condition of additional training of these models on increased number of images with objects of the “bird” class so that they satisfy the requirement for the accuracy of detecting flying objects of each four classes.

  3. Tarasov A.E., Serdobintsev E.V.
    Simulation of rail vehicles ride in Simpack Rail on the curved track
    Computer Research and Modeling, 2019, v. 11, no. 2, pp. 249-263

    The paper studies the determination for one of the dynamic quality parameter (PDK) of railway vehicles — car body lateral acceleration — by using of computer simulation system for railway vehicles dynamic Simpack Rail. This provide the complex simulation environment with variable velocity depending on the train schedule. The rail vehicle model of typical 1520 mm gauge fright locomotive section used for simulation has been verified by means of the chair “Electric multiple unit cars and locomotives” in the Russian University of Transport (RUT (MIIT)). Due to this homologation the questions of model creating and verification in preprocessor are excluded in this paper. The paper gives the detail description of cartographic track modeling in situation plane, heights plane and superelevation plane based on the real operating data. The statistic parameters (moments) for the rail related track excitation and used cartographic track data of the specified track section in this simulation are given as a numeric and graphical results of reading the prepared data files. The measurement of the car body residual lateral acceleration occur under consideration of the earth gravity acceleration part like the accelerometer measurement in the real world. Finally the desired quality parameter determined by simulation is compared with the same one given by a test drive. The calculation method in both cases is based on the middle value of the absolute maximums picked up within the nonstationary realizations of this parameter. Compared results confirm that this quality factor all the first depends on the velocity and track geometry properties. The simulation of the track in this application uses the strong conformity original track data of the test ride track section. The accepted simplification in the rail vehicle model of fright electric locomotive section (body properties related to the center of gravity, small displacements between the bodies) by keeping the geometric and force law characteristics of the force elements and constraints constant allow in Simpack Rail the simulation with necessary validity of system behavior (reactions).

    Views (last year): 20.
  4. Emaletdinova L.Y., Mukhametzyanov Z.I., Kataseva D.V., Kabirova A.N.
    A method of constructing a predictive neural network model of a time series
    Computer Research and Modeling, 2020, v. 12, no. 4, pp. 737-756

    This article studies a method of constructing a predictive neural network model of a time series based on determining the composition of input variables, constructing a training sample and training itself using the back propagation method. Traditional methods of constructing predictive models of the time series are: the autoregressive model, the moving average model or the autoregressive model — the moving average allows us to approximate the time series by a linear dependence of the current value of the output variable on a number of its previous values. Such a limitation as linearity of dependence leads to significant errors in forecasting.

    Mining Technologies using neural network modeling make it possible to approximate the time series by a nonlinear dependence. Moreover, the process of constructing of a neural network model (determining the composition of input variables, the number of layers and the number of neurons in the layers, choosing the activation functions of neurons, determining the optimal values of the neuron link weights) allows us to obtain a predictive model in the form of an analytical nonlinear dependence.

    The determination of the composition of input variables of neural network models is one of the key points in the construction of neural network models in various application areas that affect its adequacy. The composition of the input variables is traditionally selected from some physical considerations or by the selection method. In this work it is proposed to use the behavior of the autocorrelation and private autocorrelation functions for the task of determining the composition of the input variables of the predictive neural network model of the time series.

    In this work is proposed a method for determining the composition of input variables of neural network models for stationary and non-stationary time series, based on the construction and analysis of autocorrelation functions. Based on the proposed method in the Python programming environment are developed an algorithm and a program, determining the composition of the input variables of the predictive neural network model — the perceptron, as well as building the model itself. The proposed method was experimentally tested using the example of constructing a predictive neural network model of a time series that reflects energy consumption in different regions of the United States, openly published by PJM Interconnection LLC (PJM) — a regional network organization in the United States. This time series is non-stationary and is characterized by the presence of both a trend and seasonality. Prediction of the next values of the time series based on previous values and the constructed neural network model showed high approximation accuracy, which proves the effectiveness of the proposed method.

  5. Kutalev A.A., Lapina A.A.
    Modern ways to overcome neural networks catastrophic forgetting and empirical investigations on their structural issues
    Computer Research and Modeling, 2023, v. 15, no. 1, pp. 45-56

    This paper presents the results of experimental validation of some structural issues concerning the practical use of methods to overcome catastrophic forgetting of neural networks. A comparison of current effective methods like EWC (Elastic Weight Consolidation) and WVA (Weight Velocity Attenuation) is made and their advantages and disadvantages are considered. It is shown that EWC is better for tasks where full retention of learned skills is required on all the tasks in the training queue, while WVA is more suitable for sequential tasks with very limited computational resources, or when reuse of representations and acceleration of learning from task to task is required rather than exact retention of the skills. The attenuation of the WVA method must be applied to the optimization step, i. e. to the increments of neural network weights, rather than to the loss function gradient itself, and this is true for any gradient optimization method except the simplest stochastic gradient descent (SGD). The choice of the optimal weights attenuation function between the hyperbolic function and the exponent is considered. It is shown that hyperbolic attenuation is preferable because, despite comparable quality at optimal values of the hyperparameter of the WVA method, it is more robust to hyperparameter deviations from the optimal value (this hyperparameter in the WVA method provides a balance between preservation of old skills and learning a new skill). Empirical observations are presented that support the hypothesis that the optimal value of this hyperparameter does not depend on the number of tasks in the sequential learning queue. And, consequently, this hyperparameter can be picked up on a small number of tasks and used on longer sequences.

  6. Shabanov A.E., Petrov M.N., Chikitkin A.V.
    A multilayer neural network for determination of particle size distribution in Dynamic Light Scattering problem
    Computer Research and Modeling, 2019, v. 11, no. 2, pp. 265-273

    Solution of Dynamic Light Scattering problem makes it possible to determine particle size distribution (PSD) from the spectrum of the intensity of scattered light. As a result of experiment, an intensity curve is obtained. The experimentally obtained spectrum of intensity is compared with the theoretically expected spectrum, which is the Lorentzian line. The main task is to determine on the basis of these data the relative concentrations of particles of each class presented in the solution. The article presents a method for constructing and using a neural network trained on synthetic data to determine PSD in a solution in the range of 1–500 nm. The neural network has a fully connected layer of 60 neurons with the RELU activation function at the output, a layer of 45 neurons and the same activation function, a dropout layer and 2 layers with 15 and 1 neurons (network output). The article describes how the network has been trained and tested on synthetic and experimental data. On the synthetic data, the standard deviation metric (rmse) gave a value of 1.3157 nm. Experimental data were obtained for particle sizes of 200 nm, 400 nm and a solution with representatives of both sizes. The results of the neural network and the classical linear methods are compared. The disadvantages of the classical methods are that it is difficult to determine the degree of regularization: too much regularization leads to the particle size distribution curves are much smoothed out, and weak regularization gives oscillating curves and low reliability of the results. The paper shows that the neural network gives a good prediction for particles with a large size. For small sizes, the prediction is worse, but the error quickly decreases as the particle size increases.

    Views (last year): 16.
  7. Nikulin A.S., ZHediaevskii D.N., Fedorova E.B.
    Applying artificial neural network for the selection of mixed refrigerant by boiling curve
    Computer Research and Modeling, 2022, v. 14, no. 3, pp. 593-608

    The paper provides a method for selecting the composition of a refrigerant with a given isobaric cooling curve using an artificial neural network (ANN). This method is based on the use of 1D layers of a convolutional neural network. To train the neural network, we applied a technological model of a simple heat exchanger in the UniSim design program, using the Peng – Robinson equation of state.We created synthetic database on isobaric boiling curves of refrigerants of different compositions using the technological model. To record the database, an algorithm was developed in the Python programming language, and information on isobaric boiling curves for 1 049 500 compositions was uploaded using the COM interface. The compositions have generated by Monte Carlo method. Designed architecture of ANN allows select composition of a mixed refrigerant by 101 points of boiling curve. ANN gives mole flows of mixed refrigerant by composition (methane, ethane, propane, nitrogen) on the output layer. For training ANN, we used method of cyclical learning rate. For results demonstration we selected MR composition by natural gas cooling curve with a minimum temperature drop of 3 К and a maximum temperature drop of no more than 10 К, which turn better than we predicted via UniSim SQP optimizer and better than predicted by $k$-nearest neighbors algorithm. A significant value of this article is the fact that an artificial neural network can be used to select the optimal composition of the refrigerant when analyzing the cooling curve of natural gas. This method can help engineers select the composition of the mixed refrigerant in real time, which will help reduce the energy consumption of natural gas liquefaction.

  8. Petrov M.N., Zimina S.V., Dyachenko D.L., Dubodelov A.V., Simakov S.S.
    Dual-pass Feature-Fused SSD model for detecting multi-scale images of workers on the construction site
    Computer Research and Modeling, 2023, v. 15, no. 1, pp. 57-73

    When recognizing workers on images of a construction site obtained from surveillance cameras, a situation is typical in which the objects of detection have a very different spatial scale relative to each other and other objects. An increase in the accuracy of detection of small objects can be achieved by using the Feature-Fused modification of the SSD detector. Together with the use of overlapping image slicing on the inference, this model copes well with the detection of small objects. However, the practical use of this approach requires manual adjustment of the slicing parameters. This reduces the accuracy of object detection on scenes that differ from the scenes used in training, as well as large objects. In this paper, we propose an algorithm for automatic selection of image slicing parameters depending on the ratio of the characteristic geometric dimensions of objects in the image. We have developed a two-pass version of the Feature-Fused SSD detector for automatic determination of optimal image slicing parameters. On the first pass, a fast truncated version of the detector is used, which makes it possible to determine the characteristic sizes of objects of interest. On the second pass, the final detection of objects with slicing parameters selected after the first pass is performed. A dataset was collected with images of workers on a construction site. The dataset includes large, small and diverse images of workers. To compare the detection results for a one-pass algorithm without splitting the input image, a one-pass algorithm with uniform splitting, and a two-pass algorithm with the selection of the optimal splitting, we considered tests for the detection of separately large objects, very small objects, with a high density of objects both in the foreground and in the background, only in the background. In the range of cases we have considered, our approach is superior to the approaches taken in comparison, allows us to deal well with the problem of double detections and demonstrates a quality of 0.82–0.91 according to the mAP (mean Average Precision) metric.

  9. Subbotina A.Y., Khokhlov N.I.
    MPI implementations of Conway’s Game of Life and Kohomoto-Oono cellular automata
    Computer Research and Modeling, 2010, v. 2, no. 3, pp. 319-322

    Results obtained during practical training session on MPI during high perfomance computing summer school MIPT-2010 are discussed. MPI technology were one of technologies proposed to participants for realization of project. 3D version of Conway’s Game of Life was proposed as a project. Algorithms used in the development, theoretical and practical assessment of their scalability is analyzed.

    Views (last year): 11.
  10. Alekseenko A.E., Kazennov A.M.
    CUDA and OpenCL implementations of Conway’s Game of Life cellular automata
    Computer Research and Modeling, 2010, v. 2, no. 3, pp. 323-326

    In this article the experience of reading “CUDA and OpenCL programming” course during high perfomance computing summer school MIPT-2010 is analyzed. Content of lectures and practical tasks, as well as manner of presenting of the material are regarded. Performance issues of different algorithms implemented by students at practical training session are dicussed.

    Views (last year): 9. Citations: 3 (RSCI).
Pages: previous next last »

Indexed in Scopus

Full-text version of the journal is also available on the web site of the scientific electronic library eLIBRARY.RU

The journal is included in the Russian Science Citation Index

The journal is included in the RSCI

International Interdisciplinary Conference "Mathematics. Computing. Education"