Stable Parallel Algorithms for Interdisciplinary Computer-Based Online Education with Real Problem Scenarios for STEM Education

In this paper, we analyse and study the interdisciplinary style of stable parallel algorithms for online computer education and real problem scenarios for STEM education. Under the guidance of the STEM concept, the project theme is designed based on the principles of project design, and the interdis...

Full description

Saved in:
Bibliographic Details
Main Authors: Liangfu Jiang, Haoran Yuan
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2021/5432703
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467759330590720
author Liangfu Jiang
Haoran Yuan
author_facet Liangfu Jiang
Haoran Yuan
author_sort Liangfu Jiang
collection DOAJ
description In this paper, we analyse and study the interdisciplinary style of stable parallel algorithms for online computer education and real problem scenarios for STEM education. Under the guidance of the STEM concept, the project theme is designed based on the principles of project design, and the interdisciplinary knowledge points related to the theme are determined. Based on the project theme, the teaching design model of the STEM-based robotics project was constructed. The analysis of the results showed that the STEM-based middle-school robotics project not only increased students’ interest in robotics but also promoted their creativity, problem-solving, teamwork, and communication skills, as well as their learning of other subjects. In this paper, an adaptive overflow-aware loss amplification strategy is proposed, which effectively alleviates the training nonconvergence problem caused by gradient overflow in mixed accuracy training. Also, this paper demonstrates that data-parallel training under multiple machines and multiple cards should use local batch normalization, which is particularly effective in accelerating neural networks containing more batch normalization layers.
format Article
id doaj-art-e5e3e5e4316142898125747eb461a340
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-e5e3e5e4316142898125747eb461a3402025-08-20T03:26:04ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/54327035432703Stable Parallel Algorithms for Interdisciplinary Computer-Based Online Education with Real Problem Scenarios for STEM EducationLiangfu Jiang0Haoran Yuan1College of Educational Science of Hunan Normal University, Changsha, Hunan 410081, ChinaCollege of Educational Science of Hunan Normal University, Changsha, Hunan 410081, ChinaIn this paper, we analyse and study the interdisciplinary style of stable parallel algorithms for online computer education and real problem scenarios for STEM education. Under the guidance of the STEM concept, the project theme is designed based on the principles of project design, and the interdisciplinary knowledge points related to the theme are determined. Based on the project theme, the teaching design model of the STEM-based robotics project was constructed. The analysis of the results showed that the STEM-based middle-school robotics project not only increased students’ interest in robotics but also promoted their creativity, problem-solving, teamwork, and communication skills, as well as their learning of other subjects. In this paper, an adaptive overflow-aware loss amplification strategy is proposed, which effectively alleviates the training nonconvergence problem caused by gradient overflow in mixed accuracy training. Also, this paper demonstrates that data-parallel training under multiple machines and multiple cards should use local batch normalization, which is particularly effective in accelerating neural networks containing more batch normalization layers.http://dx.doi.org/10.1155/2021/5432703
spellingShingle Liangfu Jiang
Haoran Yuan
Stable Parallel Algorithms for Interdisciplinary Computer-Based Online Education with Real Problem Scenarios for STEM Education
Complexity
title Stable Parallel Algorithms for Interdisciplinary Computer-Based Online Education with Real Problem Scenarios for STEM Education
title_full Stable Parallel Algorithms for Interdisciplinary Computer-Based Online Education with Real Problem Scenarios for STEM Education
title_fullStr Stable Parallel Algorithms for Interdisciplinary Computer-Based Online Education with Real Problem Scenarios for STEM Education
title_full_unstemmed Stable Parallel Algorithms for Interdisciplinary Computer-Based Online Education with Real Problem Scenarios for STEM Education
title_short Stable Parallel Algorithms for Interdisciplinary Computer-Based Online Education with Real Problem Scenarios for STEM Education
title_sort stable parallel algorithms for interdisciplinary computer based online education with real problem scenarios for stem education
url http://dx.doi.org/10.1155/2021/5432703
work_keys_str_mv AT liangfujiang stableparallelalgorithmsforinterdisciplinarycomputerbasedonlineeducationwithrealproblemscenariosforstemeducation
AT haoranyuan stableparallelalgorithmsforinterdisciplinarycomputerbasedonlineeducationwithrealproblemscenariosforstemeducation