arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.10337cs.AIcs.LG
收藏

机器学习中知识与数据的集成

Integration of knowledge and data in machine learning

Eastern Institute for Advanced Study(东方高等研究院);Yongriver Institute of Technology(甬江理工学院);National Center for Applied Mathematics Shenzhen (NCAMS)(深圳国家应用数学中心);Southern University of Science and Technology(南方科技大学);Peng Cheng Laboratory(鹏城实验室)

Yuntian Chen, Dongxiao Zhang

摘要:

科学研究的任务是理解和探索世界,并根据经验和知识对其进行改进。知识嵌入和知识发现是知识与数据集成的两种重要方法。通过知识嵌入,可以消除知识和数据之间的壁垒,建立具有物理常识的机器学习模型。同时,人类对世界的理解总是有限的,知识发现利用机器学习从观察中提取新的知识。知识发现不仅可以帮助研究者更好地把握物理学的本质,而且可以支持他们进行知识嵌入研究。将知识嵌入和知识发现相结合,形成知识生成和使用的闭环,提高模型的鲁棒性和准确性,揭示未知的科学原理。本研究总结和分析了现存的文献,以及确定研究的差距和未来的机会。

英文摘要:

Scientific research's mandate is to comprehend and explore the world, as well as to improve it based on experience and knowledge. Knowledge embedding and knowledge discovery are two significant methods of integrating knowledge and data. Through knowledge embedding, the barriers between knowledge and data can be eliminated, and machine learning models with physical common sense can be established. Meanwhile, humans' understanding of the world is always limited, and knowledge discovery takes advantage of machine learning to extract new knowledge from observations. Knowledge discovery can not only assist researchers to better grasp the nature of physics, but it can also support them in conducting knowledge embedding research. A closed loop of knowledge generation and usage are formed by combining knowledge embedding with knowledge discovery, which can improve the robustness and accuracy of models and uncover previously unknown scientific principles. This study summarizes and analyzes extant literature, as well as identifies research gaps and future opportunities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑