Abstract

Рассматривается модель машинного обучения для предсказания существования рёбер в графе онтологии, основанная на использовании генеративно-состязательной сети. Проведены вычислительные эксперименты для различных наборов значений гиперпараметров модели. Показано, что модель решает поставленную задачу. Сформулированы направления дальнейшего развития данного подхода. A machine learning model for edge existence prediction in an ontology graph, based on generative adversarial networks, is considered. Computational experiments for different sets of hyper parameter values are fulfilled. It is shown that the model solves the task. Further steps on this approach research are formulated.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.