Neural network technologies are successfully used in solving problems from various areas of the economy - industry, agriculture, medicine. The problems of substantiating the choice of architecture and hyperparameters of artificial neural networks (ins) aimed at solving various classes of applied problems are caused by the need to improve the quality and speed of deep ins training. Various methods of optimizing ins hyperparameters are known, for example, using genetic algorithms, but this requires writing additional software. To optimize the process of selecting hyperparameters, Google research has developed the KerasTuner Toolkit, which is a user-friendly platform for automated search for optimal hyperparameter combinations. In the described Kerastuner Toolkit, you can use random search, Bayesian optimization, or Hyperband methods. In numerical experiments, 14 hyperparameters varied: the number of blocks of convolutional layers and their forming filters, the type of activation functions, the parameters of the «dropout» regulatory layers, and others. The studied tools demonstrated high optimization efficiency while simultaneously varying more than a dozen parameters of the convolutional network, while the calculation time on the Colaboratory platform for the studied INM architectures was several hours, even with the use of GPU graphics accelerators. For ins focused on processing and recognizing text information in natural language (NLP), the recognition quality has been improved to 83-92%.
The purpose of the article is to develop a model of ecological security of a state. This purpose can be reached with the help of the following methods: induction, deduction, synthesis, comparative and problem analysis, modeling, and systemic approach.The authors analyze the modern situation in the global economy and determine the reasons for provision of ecological security. The authors consider the currents notions of national security and ecological security and determine the role of economic security in provision of national security of the state. As a result of the research, the authors concluded that the objective situation in modern global economy stipulates the necessity for provision of ecological security. In order to solve a variety of ecological problems, created by anthropogenous influence, the authors developed the model of ecological security of the state, the key instruments of which are ecological marking and ecological taxation. The offered tools of ecological marking and introducing ecological taxes throughout the world will ensure the efficiency of managing the ecological security, as they will form the internal moral motivation of economic agents for support for ecological security and external material stimulation. Implementation of the developed model of ecological security of the state will allow using the market tools of providing ecological security, through forming the demand for ecologically clean products due to the systems of ecological markings and due to mechanisms of state regulation of economy through the tax system, which ensures the complexity and efficiency of the developed model.
The purpose of the research is to develop and computer implementation of methods of data mining based on cognitive modeling, obtained as a result of matrix modeling and assessment of the level of food security (FS) in conditions of forced import substitution and increased food exports. As the basic methodology for obtaining an objective assessment of the FS level, a systemic approach was used, as well as separate methods of analysis and structural synthesis of elements of the modeling system. The identification of specific differences of the updated FS Doctrine (2020) was carried out using the method of comparative research. Fuzzy cognitive maps (FCMs) were used as a basic modeling tool. The construction of the graph structure, relationships and weights of the FCM was carried out by means of a previously formed system of indicators. It has been shown that to solve the problem of objective assessment of the FS level, it is advisable to use computer modeling based on fuzzy production cognitive maps. The advisability of integral consideration of key groups of factors is justified: food production, consumption, as well as the share of imports and the rational amount of food reserves in conditions of forced import substitution. The directions of computer system modernization and improvement of mining methods for level prediction are presented. An example of FCM and a diagram of the evolution of the FS support system in pandemic conditions are given.
PurposeThe article considers the causes of such a fundamental problem like poverty.Design/methodology/approachThe authors analyzed the interdependence of poverty and the development of the digital economy, and also examined possible ways to develop measures to reduce the spread of poverty.FindingsAn algorithm is proposed for diagnosing the level of poverty development, and a mechanism has been developed to reduce it due to the development of self-employment of the population.Originality/valueThe main scientific task to be solved by the study is to improve the quality of life of the population of the regions of Russia by reducing poverty and increasing employment in the form of self-employment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.