大学物理 ›› 2026, Vol. 45 ›› Issue (6): 79-.doi: 10.16854/j.cnki.1000-0712.250368

• AI赋能 智教新探 • 上一篇    下一篇

物理课程与神经网络融合的教学设计

孙林锋,李军刚   

  1. 北京理工大学 物理学院,北京100081
  • 收稿日期:2025-07-16 接受日期:2025-10-31 出版日期:2026-08-01 发布日期:2026-08-28
  • 作者简介:孙林锋(1987—),男,北京理工大学物理学院教授,博士,主要从事大学物理教学和面向存算一体器件的量子功能材料物性调控及其在类脑计算器件上的应用方面的研究.


  • 基金资助:
    北京市高等教育学会2025年立项面上课题(MS2025121),北京市高等教育学会2024年立项课题(MS2024078)

Teaching design for integrating physics courses with neural networks

SUN Linfeng, LI Jungang   

  1. School of Physics, Beijing Institute of Technology, Beijing 100081, China
  • Received:2025-07-16 Accepted:2025-10-31 Online:2026-08-01 Published:2026-08-28

摘要: 近年来,人工智能技术迅速发展,2024年诺贝尔物理学奖授予在人工神经网络与机器学习领域做出开创性贡献的科学家,进一步凸显了物理学与前沿科技之间的深刻关联.本文探索将神经网络技术引入物理课程的教学设计路径,旨在丰富教学内容,增强课程前沿性与科技关联性,激发学生学习兴趣,从而提升物理课程的教学质量与育人实效.本研究强调神经网络与物理知识体系的可结合性,为物理课程教学内容的创新与拓展提供了借鉴.

关键词: 人工智能, 神经网络, 物理课程, 教学设计

Abstract: In recent years, artificial intelligence technology has developed rapidly. The 2024 Nobel Prize in Physics was awarded to scientists for their groundbreaking contributions in the fields of artificial neural networks and machine learning, further underscoring the deep connection between physics and cutting-edge technologies. This paper explores a teaching design that integrates neural network technology into physics courses, aiming to enrich course content, enhance the cutting-edge nature and technological relevance of the course, stimulate student interest, and ultimately improve the quality and effectiveness of physics courses. This study emphasizes the integration potential of neural networks with the physics knowledge system, providing a reference for the innovation and expansion of physics course content.


Key words: artificial intelligence, neural networks, physics courses, teaching design