Multifunctional and flexible online platforms for creating educational materials

Author:

Nikandrov A. A.1ORCID

Affiliation:

1. The Herzen State Pedagogical University of Russia

Abstract

The article actualizes the need to use multifunctional flexible online platforms to promote educational activities, in particular the discipline “Machine Learning”. The main characteristic features of the discipline “Machine Learning” are described, the teaching of which consists in a task-based approach through writing program codes in a programming language, which is the Python 3 interpreter with a bundle of libraries selected: NumPy, Pandas, Matplotlib and Seaborn for data processing and visualization. The Scikit-learn library is used directly for machine learning. In addition to the Python 3 interpreter, coding tools are involved, namely: the PyCharm Community cross-platform development environment and the Jupyter Notebook open source web application. The potential of educational multifunctional flexible online platforms including designers of open online courses to facilitate independent learning of students is evaluated. According to the versions of various domestic and foreign scientific publications, the most mentioned online platforms are identified, their functionality regarding the placement of material in the fields of programming and machine learning was analyzed. Based on the analysis of the functional, a group of potential basic requirements for educational platforms in teaching programming within the discipline “Machine Learning” was identified, analyzed and discussed.

Publisher

Publishing House Education and Informatics

Subject

General Medicine

Reference25 articles.

1. Noskova T. N., Pavlova T. B., Yakovleva O. V. ICT tools of professional teacher activity: A comparative analysis of Russian and European experience. Integration of Education. 2018;22(1):25–45. (In Russian.) DOI: 10.15507/1991-9468.090.022.201801.025-045]

2. Trapp S. Blended learning concepts — a short overview. Proceedings of the EC-TEL06 Workshops. Crete (Greece): CEUR-WS.org. 2006:28–35. Available at: https://ceur-ws.org/Vol-213/paper7.pdf

3. Piotrowska X., Terbusheva E. Educational data mining for future educational employees. CEUR Workshop Proceedings: 14th International Conference “New Educational Strategies in Modern Information Space” (NESinMIS-2019). Saint Petersburg, 2019:38–49. Available at: https://www.elibrary.ru/item.asp?id=41645157

4. Коэльо Л. П., Ричарт В. Построение систем машинного обучения на языке Python. М.: ДМК-Пресс; 2016. 302 с.

5. Vorontsov K. V. Machine Learning. Course of lectures. (In Russian.) Available at: http://www.machinelearning.ru/wiki/index.php?title=Машинное_обучение_(курс_лекций%2C_К.В.Воронцов)]

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3