Highly available systems最新文献

Modeling of nonstationary random processes and search engine optimization processes on simulation models of queuing systems 非平稳随机过程和搜索引擎优化过程在排队系统仿真模型上的建模

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j19997493-202201-01

V. Stroganov, V. Chernenky, V. Mikheev

引用次数: 0

The methodology of proactive aviation safety management and the formation of reliable predictive assessments of the level of flight safety 主动航空安全管理的方法学和形成可靠的飞行安全水平预测评估

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j20729472-202201-04

V. Belenkov, M. V. Volkov, D.A. Godikov, A. V. Kan

引用次数: 1

Improving the efficiency of working with a web resource due to the tools of a system programmer 由于系统程序员的工具，提高了使用网络资源的效率

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j19997493-202203-03

B. Goryachkin, T.I. Khanmurzin

引用次数: 0

System for distributed training of Kernel forests 分布式训练核心林系统

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j20729472-202203-05

D. Devyatkin

引用次数: 0

Signal processing algorithm for neural networks with integrodifferential splines as an activation function and its particular case of image classification 以积分微分样条为激活函数的神经网络信号处理算法及其图像分类实例

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j20729472-202102-02

T.K. Biryukova

{"title":"Signal processing algorithm for neural networks with integrodifferential splines as an activation function and its particular case of image classification","authors":"T.K. Biryukova","doi":"10.18127/j20729472-202102-02","DOIUrl":"https://doi.org/10.18127/j20729472-202102-02","url":null,"abstract":"Classic neural networks suppose trainable parameters to include just weights of neurons. This paper proposes parabolic integrodifferential splines (ID-splines), developed by author, as a new kind of activation function (AF) for neural networks, where ID-splines coefficients are also trainable parameters. Parameters of ID-spline AF together with weights of neurons are vary during the training in order to minimize the loss function thus reducing the training time and increasing the operation speed of the neural network. The newly developed algorithm enables software implementation of the ID-spline AF as a tool for neural networks construction, training and operation. It is proposed to use the same ID-spline AF for neurons in the same layer, but different for different layers. In this case, the parameters of the ID-spline AF for a particular layer change during the training process independently of the activation functions (AFs) of other network layers. In order to comply with the continuity condition for the derivative of the parabolic ID-spline on the interval (x x0, n) , its parameters fi (i= 0,...,n) should be calculated using the tridiagonal system of linear algebraic equations: To solve the system it is necessary to use two more equations arising from the boundary conditions for specific problems. For exam- ple the values of the grid function (if they are known) in the points (x x0, n) may be used for solving the system above: f f x0 = ( 0) , f f xn = ( n) . The parameters Iii+1 (i= 0,...,n−1 ) are used as trainable parameters of neural networks. The grid boundaries and spacing of the nodes of ID-spline AF are best chosen experimentally. The optimal selection of grid nodes allows improving the quality of results produced by the neural network. The formula for a parabolic ID-spline is such that the complexity of the calculations does not depend on whether the grid of nodes is uniform or non-uniform. An experimental comparison of the results of image classification from the popular FashionMNIST dataset by convolutional neural 0, x< 0 networks with the ID-spline AFs and the well-known ReLUx( ) =AF was carried out. The results reveal that the usage x x, ≥ 0 of the ID-spline AFs provides better accuracy of neural network operation than the ReLU AF. The training time for two convolutional layers network with two ID-spline AFs is just about 2 times longer than with two instances of ReLU AF. Doubling of the training time due to complexity of the ID-spline formula is the acceptable price for significantly better accuracy of the network. Wherein the difference of an operation speed of the networks with ID-spline and ReLU AFs will be negligible. The use of trainable ID-spline AFs makes it possible to simplify the architecture of neural networks without losing their efficiency. The modification of the well-known neural networks (ResNet etc.) by replacing traditional AFs with ID-spline AFs is a promising approach to increase the neural network operation","PeriodicalId":156447,"journal":{"name":"Highly available systems","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123392950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Creation of an information management system for food industry enterprises in the CRM concept 在CRM理念下，为食品工业企业创建了一个信息管理系统

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j19997493-202202-03

V. Novitsky, A. Semenov

引用次数: 0

Comparatives assessments of the main indicators defining the conditions for the artificial intelligence industry development in the Russian Federation, USA and PRC 对俄罗斯联邦、美国和中国人工智能产业发展条件主要指标的比较评估

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j19997493-202203-06

A. E. Nikolaev, I. A. Abramov

引用次数: 0

Graphic dynamic modelling of information telecommunication network in interests of a rational distribution of resources 信息通信网络的图形动态建模有利于资源的合理配置

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j19997493-202203-04

D.A. Tavalinskiy, D.A. Krasikov

引用次数: 0

Intellectual capabilities of cluster analysis 5G-6G Transition Neuroprocessor Resource Architectures 聚类分析5G-6G过渡神经处理器资源架构的智能能力

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j19997493-202202-02

V. Ruchkin, B. Kostrov, V. Fulin

引用次数: 0

The approach to increasing the efficiency of convolution algorithms in modern high-availability systems 在现代高可用性系统中提高卷积算法效率的方法

Highly available systems Pub Date : 1900-01-01 DOI: 10.18127/j20729472-202101-02

E. Goncharov, P. Iljin, V. Munerman, T. A. Samoylova

{"title":"The approach to increasing the efficiency of convolution algorithms in modern high-availability systems","authors":"E. Goncharov, P. Iljin, V. Munerman, T. A. Samoylova","doi":"10.18127/j20729472-202101-02","DOIUrl":"https://doi.org/10.18127/j20729472-202101-02","url":null,"abstract":"Most modern high-availability information systems are either based on systems that are classified as artificial intelligence, or to a large extent include them as components. The solution of many problems of artificial intelligence is based on the use of algorithms that implement the convolution operation (for example, algorithms for training neural networks). The article proposes an approach that, on the one hand, provides a strict formalization of this operation based on the algebra of multidimensional matrices, and on the other hand, due to this, it provides such practical advantages as simplifying and reducing the cost of developing such information systems, as well as reducing the execution time of queries to them. due to the simplicity of the development of parallel algorithms and programs and the efficient use of parallel computing systems. Convolution is an indispensable operation for solving many scientific and technical problems, such as machine learning, data analysis, signal processing, image processing filters. An important role is played by multidimensional convolutions, which are widely used in various subject areas. At the same time, due to the complexity of the algorithms that implement them, in practice even three-dimensional convolutions are used much less frequently than one- and two-dimensional ones. Replacing a multidimensional convolution operation with a sequence of convolution operations of lower dimensions significantly increases its computational complexity. The main reason for this lies in the absence of a unified strict definition of the operation and overload in mathematics of the term «convolution». Therefore, the article discusses a multidimensional-matrix computation model, which allows one to effectively formalize problems whose solution uses multidimensional convolution operations, and to implement an effective solution to these problems due to the natural parallelism inherent in the operations of the algebra of multidimensional matrices.","PeriodicalId":156447,"journal":{"name":"Highly available systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126296592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0