×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

  • An overview of service tools based on machine learning for writing program source code

    In recent years, the use of various tools based on machine learning in the process of writing the source code of various programs, interfaces, and websites has been gaining momentum. These include programs that help in testing applications, programs that analyze the developer's code, as well as assistant programs that help write code right in the process, predicting and prompting the developer with options for the finished program code. In this article, just the same, such assistant programs will be considered in order to analyze the shortcomings and justify the need to develop functionality in this direction.

    Keywords: source code, machine learning, neural networks, application testing problem, natural language processing

  • Formation and analysis of the efficiency of the dataset for teaching language models to recognize and analyze the source code of programs

    This article describes the formation of a training set for training language neural networks for their use in tasks related to the analysis and search for matches and / or correspondences in meaning / value, and specifically with functions and methods in the source code of a programming language. The key parameters required in the sample for the correct training of the neural network are determined.

    Keywords: source code, machine learning, natural language processing, neural network, data analysis