課程名稱 |
機器學習中的數學原理 Mathematical Principles of Machine Learning |
開課學期 |
107-2 |
授課對象 |
電機資訊學院 電機工程學研究所 |
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)星期四3,4(10:20~12:10) |
上課地點 |
電二106電二106 |
備註 |
本課程以英語授課。上課時間:週二及週四早上10:30~12:00 總人數上限:60人 |
課程網頁 |
https://cool.ntu.edu.tw/courses/204 |
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 |
This course aims to introduce some theoretical foundations of machine learning. The course is roughly divided into two parts: (1) the statistical principles and (2) the algorithmic principles. For the former, we will focus on statistical aspects of learning theory, where the main themes are what can be learned and how well a machine can learn from a finite number of training samples. For the latter, we focus on algorithmic aspects of learning theory, where the main theme is how fast a machine can learn with theoretical performance guarantees. |
課程目標 |
1. Introduce main concepts underlying machine learning with mathematical rigor.
2. Uncover mathematical principles underlying various machine learning techniques.
3. Introduce methods to theoretically analyze learning algorithms.
4. Develop theory-oriented thinking which helps understand existing algorithms and create novel ones. |
課程要求 |
Prerequisite: Calculus, Probability, Linear Algebra.
Preferable (but optional): Machine learning, Convex optimization, Real analysis.
Grading: Exam (25%), Homework (50%), Project (25%) |
預期每週課後學習時數 |
|
Office Hours |
備註: Tuesday and Wednesday, 17:30 - 18:30 |
指定閱讀 |
Lectures will be based on lecture notes and slides. |
參考書目 |
1. Shai Shalev-Shwartz and Shai Ben-David, Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, 2014.
2. Y. Nesterov, Introductory lectures on convex optimization: A basic course. Kluwer Academic Publishers, 2004.
3. Additional references: research papers and surveys to be assigned during lectures. |
評量方式 (僅供參考) |
No. |
項目 |
百分比 |
說明 |
1. |
Homework |
50% |
|
2. |
Exam |
25% |
|
3. |
Project |
25% |
|
|