本課程以物理問題為核心，介紹機器學習的基本概念、常用方法及其在現代物理研究中的應用。課程強調理解機器學習模型背後的原理與物理意義，使學生能夠判斷模型結果的合理性與侷限性，並培養運用人工智慧工具解決科學問題的能力。

透過真實物理案例分析與專題實作，學生將學習如何從資料中萃取資訊、建立適當模型、解讀分析結果，並探討機器學習在實驗物理、材料科學、統計物理、天文物理及量子科學等領域中的應用。課程同時鼓勵學生善用生成式人工智慧輔助程式開發與資料分析，並培養批判思考與自主驗證能力，以建立兼具物理素養、數據分析能力與AI應用能力的跨領域能力。

This course focuses on physical problems and introduces the basic concepts, common methods and applications of machine learning in modern physics research. The course emphasizes understanding the principles and physical meaning behind machine learning models, enabling students to judge the rationality and limitations of model results, and develop the ability to use artificial intelligence tools to solve scientific problems.

Through real physics case analysis and project implementation, students will learn how to extract information from data, build appropriate models, interpret analysis results, and explore the application of machine learning in fields such as experimental physics, materials science, statistical physics, astrophysics, and quantum science. The course also encourages students to make good use of generative artificial intelligence to assist program development and data analysis, and cultivate critical thinking and independent verification abilities to build cross-domain capabilities that combine physical literacy, data analysis capabilities, and AI application capabilities.

Machine Learning for Physics and Astronomy
作者： Acquaviva, Viviana
原文出版社：Princeton University Press

Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow
作者：Aurélien Géron
原文出版社：O’Reilly Media

Machine Learning for Physics and Astronomy
Author: Acquaviva, Viviana
Original publisher: Princeton University Press

Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow
Author: Aurélien Géron
Original publisher: O’Reilly Media