USE OF CONVOLUTIONAL NEURAL NETWORKS FOR THE TASK OF CLASSIFYING TEXTS
Journal Title: Международный научный журнал "Интернаука" - Year 2018, Vol 1, Issue 14
Abstract
Convolutional neural networks are a powerful tool of machine learning, which is aimed at efficient recognition and classification of images. The success of using convolutional neural networks for images has given rise to many attempts to use this tool in other problems. In this paper, we study the basic methods of using convolutional neural networks for the task of classifying texts. Experiments were performed on large-scale text data, which showed that convolutional neural networks for a word classification problem can achieve a quality similar to or better than traditional methods.
Authors and Affiliations
Artem Karpovych
Keywords
Related Articles
- EP ID EP610484
- DOI 10.25313/2520-2057-2018-14-4105
- Views 100
- Downloads 0
AVTORSKAYA THE CONCEPT OF INCLUSIVE EDUCATION PRESCHOOL CHILDREN VIOLATION OF THE PSYCHOPHYSICAL DEVELOPMENT
The theoretical aspects of inclusive education of preschool children with impaired mental and psychophysical development.
ANALYSIS SYSTEM OF STATE SECRETS IN THE FEDERAL REPUBLIC OF GERMANY
Analyzed the legal framework for the protection of state secrets in the Federal Republic of Germany
THE MODEL OF REFERENCE DATA AND ITS PRACTICAL USE IN «HEALTH MONITOR» PROJECT
This article describes the object model of legal and reference data (NSI), built on the basis of existing international standards, provides a broad description of the possibilities of a cart-more properties of concepts a...
THE STUDY OF THE QUALITY OF FOOD IN RESTAURANTS
The research of the quality of dietary rations in the restaurants was conducted.
SPECIFICITY OF CONTRACTS IN THE HYBRID METHODOLOGY OF PROJECT MANAGEMENT
During all time of project management existence, a huge number of different methodologies and standards for project management have been developed. The two main areas are traditional waterfall models and flexible methodo...