課程資訊
課程名稱
 機器學習
Machine Learning 
開課學期
 108-2 
授課對象
 電信工程學研究所  
授課教師
 林宗男 
課號
 EE5184 
課程識別碼
 921 U2620 
班次
 02 
學分
 4.0 
全/半年
 半年 
必/選修
 選修 
上課時間
 星期二A,B,C,D(18:25~22:00) 
上課地點
 博理112 
備註
 初選不開放。AI資安在職專班優先選課。與李宏毅、吳沛遠合授
總人數上限：10人 
Ceiba 課程網頁
 http://ceiba.ntu.edu.tw/1082_ML 
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

待補 

課程目標
 待補 
課程要求
 待補 
預期每週課後學習時數
  
Office Hours
  
指定閱讀
 待補 
參考書目
 待補 
評量方式
(僅供參考)
    
課程進度
週次
日期
單元主題
第1週
 3/03  李宏毅的ML 影片內容: ML Lecture 0-1: Introduction of Machine Learning。
https://www.youtube.com/watch?v=CXgbekl66jc&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=1 
第2週
 3/10  ML Lecture 1: Regression
https://www.youtube.com/watch?v=fegAeph9UaA&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=3

ML Lecture 1: Regression - Demo
https://www.youtube.com/watch?v=1UqCjFQiiy0&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=4

ML Lecture 2: Where does the error come from
https://www.youtube.com/watch?=D_S6y0Jm6dQ&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=5 
第3週
 3/17  ML Lecture 3-1: Gradient Descent

https://www.youtube.com/watch?v=yKKNr-QKz2Q&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=6


ML Lecture 4: Classification

https://www.youtube.com/watch?v=fZAZUYEeIMg&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=9 
第4週
 3/24  ML Lecture 5:Logistic Regression
https://www.youtube.com/watchv=hSXFuypLukA&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=10  
第5週
 3/31  ML Lecture 20: Support Vector Machine (SVM)
https://www.youtube.com/watchv=QSEPStBgwRQ&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=29

ML Lecture 22: Ensemble
https://www.youtube.com/watch?v=tH9FH1DH5n0&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=32
 
第7週
 4/14  ML Lecture 6: Brief Introduction of Deep Learning
https://www.youtube.com/watch?v=Dr-WRlEFefw&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=11

ML Lecture 7: Back propagation
https://www.youtube.com/watch?v=ibJpTrp5mcE&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=12

ML Lecture 9-1: Tips for Training DNN
https://www.youtube.com/watch?v=xki61j7z-30&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=16
 
第8週
 4/21  Deep Learning Theory 1-1: Can shallow network fit any function?
https://www.youtube.com/watch?v=KKT2VkTdFyc&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K

Deep Learning Theory 1-2: Potential of Deep
https://www.youtube.com/watch?v=FN8jclCrqY0&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=2

Deep Learning Theory 1-3: Is Deep better than Shallow?
https://www.youtube.com/watch?v=qpuLxXrHQB4&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=3

Deep Learning Theory 2-1: When Gradient is Zero
https://www.youtube.com/watch?v=XSdkBG6Vvr0&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=4
 
第9週
 4/28  Deep Learning Theory 2-2: Deep Linear Network
https://www.youtube.com/watch?v=0O6nYRC7GeY&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=5

Deep Learning Theory 2-3: Does Deep Network have Local Minima?
https://www.youtube.com/watch?v=NmelPQkUark&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=6

Deep Learning Theory 2-4: Geometry of Loss Surfaces (Conjecture)
https://www.youtube.com/watch?v=_VuWvQUMQVk&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=7

Deep Learning Theory 2-5: Geometry of Loss Surfaces (Empirical)
https://www.youtube.com/watch?v=XysGHdNOTbg&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=8

Deep Learning Theory 3-1: Generalization Capability of Deep Learning
https://www.youtube.com/watch?v=9dtxv4HLq_8&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=9

Deep Learning Theory 3-2: Indicator of Generalization
https://www.youtube.com/watch?v=pivB5jEBOQw&list=PLJV_el3uVTsOh1F5eo9txATa4iww0Kp8K&index=10
 
第10週
 5/05  ML Lecture 10: Convolutional Neural Network
https://www.youtube.com/watch?v=FrKWiRv254g&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=19

ML Lecture 11: Why Deep?
https://www.youtube.com/watch?v=XsC9byQkUH8&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=20

ML Lecture 12: Semi-supervised
https://www.youtube.com/watch?v=fX_guE7JNnY&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=21 
第11週
 5/12  ML Lecture 13: Unsupervised Learning - Linear Methods
https://www.youtube.com/watch?v=iwh5o_M4BNU&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=22 
第12週
 5/19  ML Lecture 14: Unsupervised Learning - Word Embedding
https://www.youtube.com/watch?v=X7PH3NuYW0Q&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=23

ML Lecture 15: Unsupervised Learning - Neighbor Embedding
https://www.youtube.com/watch?v=GBUEjkpoxXc&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=24

ML Lecture 16: Unsupervised Learning - Auto-encoder
https://www.youtube.com/watch?v=Tk5B4seA-AU&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=25

ML Lecture 21-1: Recurrent Neural Network (Part I)
https://www.youtube.com/watch?v=xCGidAeyS4M&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=30
 
第13週
 5/26  ML Lecture 21-2: Recurrent Neural Network (Part II)
https://www.youtube.com/watch?v=rTqmWlnwz_0&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=31

ML Lecture 22: Ensemble
https://www.youtube.com/watch?v=tH9FH1DH5n0&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=32  
第14週
 6/02  ML Lecture 23-1: Deep Reinforcement Learning
https://www.youtube.com/watch?v=W8XF3ME8G2I&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=33

ML Lecture 23-2: Policy Gradient (Supplementary Explanation)
https://www.youtube.com/watch?v=y8UPGr36ccI&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=34

ML Lecture 23-3: Reinforcement Learning (including Q-learning)
https://www.youtube.com/watch?v=2-JNBzCq77c&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=35