本課程旨在引領學生初步探索機器學習的核心理論及其數學分析方法。本課程內容將會介紹機器學習中重要理論工具與基礎數學原理，包含：機器學習的可學習性、模型複雜度、泛化界、穩定性、一致性及收斂率等重要理論概念與分析。課程應用線性代數、微積分、機率統計與最佳化理論知識，著重培養學生嚴謹的理論思維，並介紹如何運用精確的數學技巧來分析機器學習問題。該課程特別適合希望藉由數學工具深入解析機器學習數學原理的學生修習。由於本課程聚焦於機器學習理論及其數學原理，不涵蓋各種機器學習演算法或模型的具體介紹，因此學生可另外搭配相關機器學習演算法或AI實務課程一同修讀，以獲得該領域全面的知識學習體驗。
(This course is designed to guide students in initially exploring the core theories and mathematical analysis methods underlying machine learning. The curriculum introduces essential theoretical tools and mathematical principles in machine learning, including learnability, model complexity, generalization bounds, stability, consistency, and convergence rates, among other key concepts and analyses. Drawing upon knowledge from linear algebra, calculus, probability and statistics, and optimization theory, the course emphasizes the development of rigorous theoretical thinking and demonstrates how to apply precise mathematical techniques to analyze machine learning problems. This course is particularly suited for students who wish to delve rigorously into the mathematical foundations of machine learning using robust mathematical tools. As the focus is on theoretical principles and mathematical foundations rather than on introducing various machine learning algorithms or models, students are encouraged to complement their studies with related courses on machine learning algorithms or practical AI applications for a more complete learning experience.)