課程資訊
課程名稱
機器學習中的數學原理
Mathematical Principles of Machine Learning 
開課學期
110-1 
授課對象
電機資訊學院  電信工程學研究所  
授課教師
王奕翔 
課號
CommE5051 
課程識別碼
942EU0650 
班次
 
學分
3.0 
全/半年
半年 
必/選修
選修 
上課時間
星期二3,4(10:20~12:10)星期五6,7(13:20~15:10) 
上課地點
 
備註
本課程以英語授課。上課時間:二34(10:30~11:50),五67(13:50~15:10).電二106
總人數上限:24人 
課程網頁
https://cool.ntu.edu.tw/courses/9214 
課程簡介影片
 
核心能力關聯
核心能力與課程規劃關聯圖
課程大綱
為確保您我的權利,請尊重智慧財產權及不得非法影印
課程概述

Mathematical Principles of Machine Learning is a graduate level course (motivated undergraduate students are also welcome) designed for students who are interested in the theoretical foundations of machine learning. Machine learning are computational methods that leverage past experiences (data) to improve performance in making predictions and taking actions. The design of machine learning methods leads to three fundamental questions regarding representation, optimization, and generalization. In this course, we aim to introduce the underlying mathematical principles of concurrent solutions and answers to these three questions. 

課程目標
1. Introduce main concepts in machine learning methods with mathematical rigor.
2. Introduce methods to theoretically analyze learning algorithms. 
課程要求
Prerequisite: Calculus, Probability, Linear Algebra.
Preferable (but optional): Machine learning, Convex optimization, Real analysis.
Grading (tentative): Homework (50%), Exam (20%), Project (30%). 
預期每週課後學習時數
 
Office Hours
另約時間 
參考書目
1. Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar, Foundations of Machine Learning, MIT Press, Second Edition, 2018.
2. Shai Shalev-Shwartz and Shai Ben-David, Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, 2014.
3. Moritz Hardt and Benjamin Recht, Patterns, predictions, and actions: A story about machine learning, https://mlstory.org, 2021.
4. Additional references will be provided in the lectures. 
指定閱讀
Lectures will be based on slides and supplementary notes. 
評量方式
(僅供參考)
 
No.
項目
百分比
說明
1. 
Homework 
50% 
 
2. 
Exam 
20% 
 
3. 
Project 
30% 
 
 
課程進度
週次
日期
單元主題
無資料