閱讀全文 | |
篇名 |
超越碎片化学习:语义图示与深度学习
|
---|---|
並列篇名 | Go beyond the Fragmentation: Semantic Diagram and Deep Learning |
作者 | 顾小清、冯园园、胡思畅 |
中文摘要 | 泛在技术的普及使得信息的获取更加便捷,与之伴随地是信息消费中的碎片化、多任务和浅层读图的现象。针对这一问题,该文依托于“语义图示”所开展的研究,提出一个有助于提高学习深度的方案——语义图示工具模型。作为一种帮助学习者达到深层学习的工具,语义图示工具的设计超越碎片化的知识获取方式,为学习者提供系统而全面的学习支持。该文首先追溯机器学习和教育领域中深度学习的发展;接着在语义图示工具的设计中,借助人工智能技术,设计专家系统作为后台支持,以实现可视化语义建模、语义推荐以及动态模拟的核心功能,这些功能旨在通过语义图示帮助学习者做出决策、解决问题,以超越碎片化的信息获取方式;最后,该文以案例的方式呈现语义图示工具中的几个核心功能,以示例如何通过可视化的语义图示超越碎片化的语义获取。 |
英文摘要 | Wide use of technology in education enables the convenient access to much richer information, while on the other hand, produce the so called phenomenon of “fragmented learning”, when the learners frequently engage in multi-task and pick up fragmented information, among which visual are always preferred. This phenomenon resulted in shallow learning is the problem that this paper tried to focused on. A “semantic diagram” model was proposed in this study as a way to help learners achieve deep learning, which can provide learners with a systematic and comprehensive learning support, to integrate the fragmented knowledge into a systematic knowledge base. This paper reviewed the development of deep learning in the field of machine learning and education at first; then introduce the design of the semantic diagram tools based on the artificial intelligence technology, using expert system as a back-end support to visualize semantic modeling, semantic recommendation and dynamic simulation, in order to help learners make decision and solve problems. At last, this paper listed three semantic tools as examples to represent core functions and illustrate how it works to help resolve the issue of learning fragmentation. |
起訖頁 | 039-048 |
關鍵詞 | 碎片化、语义图示、深度学习、机器学习、Fragmented learning、Semantic Diagram、Deep Learning、Machine Learning |
刊名 | 中國電化教育 |
期數 | 201503 (338期) |
出版單位 | 中國電化教育雜誌社 |
該期刊 上一篇
| 大学生存危机来临还是高等教育普及开始——大学慕课研究与实践的转向与未来走向 |
該期刊 下一篇
| 媒介变迁引发学习方式变革研究 |