Development of a method for structural optimization of a neural network based on the criterion of resource utilization efficiency
Journal Title: Восточно-Европейский журнал передовых технологий - Year 2019, Vol 2, Issue 4
Abstract
<p>At present, mathematical models in the form of artificial neural networks (ANNs) are widely used to solve problems on approximation. Application of this technology involves a two-stage approach that implies determining the structure for a model of ANN and the implementation of its training. Completion of the learning process makes it possible to derive a result of the approximation whose accuracy is defined by the complexity of ANN structure. In other words, increasing the ANN complexity allows obtaining a more precise result of training.</p><p>In this case, obtaining the model of ANN that implements approximation at the assigned accuracy is defined as the process of optimization.</p><p>However, an increase in the ANN complexity leads not only to the improved accuracy, but prolongs the time of computation as well.</p><p>Thus, the indicator «assigned accuracy» cannot be used in the problems on determining the optimum neural network architecture. This relates to that the result of the model structure selection and the process of its training, based on the required accuracy of approximation, might be obtained over a period of time unacceptable for the user.</p><p>To solve the task on structural identification of a neural network, the approach is used in which the model’s configuration is determined based on a criterion of efficiency. The process of implementation of the constructed method implies adjusting a time factor related to solving the problem and the accuracy of approximation.</p>The proposed approach makes it possible to substantiate the principle of choosing the structure and parameters of a neural network based on the maximum value for the indicator of effective use of resources
Authors and Affiliations
Igor Lutsenko, Oleksii Mykhailenko, Oksana Dmytriieva, Oleksandr Rudkovsky, Denis Mospan, Dmitriy Kukharenko, Hanna Kolomits, Artem Kuzmenko
Keywords
Related Articles
- EP ID EP666302
- DOI 10.15587/1729-4061.2019.164591
- Views 107
- Downloads 0
Interlaboratory comparisons of the calibration results of signal generator
<p>The data of interlaboratory comparisons of calibration results of signal generators at three calibration points are presented. The choice of methodology for processing the results of interlaboratory comparisons is mad...
Construction of the expert system of geospatial analysis that employs scenarios for the automated data generation for a digital map
<p>This paper reports a study into the formalization of algorithms for solving problems, the generation of data for digital maps, as well as their implementation, through a set of simple operations that would be intuitiv...
Development of a highly efficient combined apparatus (a combination of vortex chambers with a bin) for dry dedusting of gases
<p>The use of dust collectors of a new type which combine the operation principle of centrifugal and louvre-vortex apparatuses was considered. The use of a heterogeneous reactor for gas-solid systems with two streams in...
Assessment and prevention of the propagation of carbon monoxide over a working area at arc welding
<p>This paper reports a study of air environment at industrial premises where welding processes take place, with special attention paid to the formation of carbon monoxide (oxide) (CO) in the working environment in the p...
Design of the architecture of an intelligent system for distributing commercial content in the internet space based on SEO-technologies, neural networks, and Machine Learning
We have considered a task on designing an intelligent system of commercial distribution of informational products using a personalized approach to visitors based on the categories and tags of content that interests visit...