課程資訊
課程名稱
 統計學習與深度學習
Statistical Learning and Deep Learning 
開課學期
 110-1 
授課對象
 管理學院  資訊管理學研究所  
授課教師
 盧信銘 
課號
 IM5056 
課程識別碼
 725 U3670 
班次
  
學分
 3.0 
全/半年
 半年 
必/選修
 選修 
上課時間
 星期四2,3,4(9:10~12:10) 
上課地點
 管二305 
備註
 總人數上限：70人 
  
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

課程加選結束，中籤名單請見 (as of 2021-9-23 10:50AM): https://bit.ly/3CcYOzF

中籤者的授權碼已經寄出。如果你有中籤但沒有收到授權碼，請跟授課教師聯絡。

本課程採全線上教學。第一次上課(2021/9/23上午9:10開始)使用Webex (已結束)，連線網址是https://ntu-mgmt.webex.com/meet/luim

Statistical learning refers to a set of tools for modeling and understanding complex datasets. It is a recently developed area in statistics and blends with parallel developments in computer sciences and machine learning. The field encompasses many methods such as the regularized regression, classification, graphic models, and recently deep learning. The goal of this course is to introduce a set of tools for data analytics. We will cover the principles and applications of these models/tools. These tools will not be viewed as black boxes. Instead, students will be exposed to the details, not just the use, of these tools. The main reason is that no single approach will perform well in all possible applications. Without understanding how a tool work, it is impossible to select the best tool. This course is appropriate for master's students and advanced undergraduates who wish to use statistical learning, machine learning, and deep learning to analyze their data. 

課程目標
 Omitted. 
課程要求
 *Grade Distribution*
The course grades will be determined by the following percentages:

Homework (Python-based) (5-6 Assignments) 55%
Attendance, participation & quizzes 15%
Final Project (Presentation) 30%
Total 100%


*Computational Tools*
Students are required to use Python 3 (Version >=3.8) (with scikit-learn, pandas, matplotlib, numpy, pytorch, etc.) to solve homework assignments.


*Homework*
There are at least five graded assignments. Unless otherwise stated, students must organize their code and results using Jupyter Lab (with Python 3; Version >=3.8) and submit their *.IPYNB file together with the exported HTML file to NTUCOOL. Other file formats are not accepted and will result in a zero score for the homework. You will have two weeks to finish each homework assignment (Due time: 12:30 pm Thursday). Late submissions will not be accepted. Homework assignments play a critical role in the learning process, and students are expected to spend a significant amount of time in solving homework problems. Note that plagiarism will result in a severe penalty for everyone involved.

*Final Project (Team-based)*
Students are expected to form teams of three to six people and work on a data analytics problem that is interesting and challenging for you. Details will be given in class. 
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
 9/23  Introduction, Regression Part 1 (K-nearest-neighbors) 
第2週
 9/30  Regression Parts 2-3 (Linear models and regularization) 
第3週
 10/07  Regression Part2 4-6: Dummy coding, bias-variance trade off, and an example 
第4週
 10/14  Linear Models for Classification 
第5週
 10/21  Model Evaluation 
第6週
 10/28  Feature Selection 
第7週
 11/04  Dimension Reduction 
第8週
 11/11  Tree-based Models, Part 1 
第9週
 11/18  Tree-based Models, Part 2: Bagging, Random Forest, Boosting, and Stacking 
第10週
 11/25  Deep Feedforward Networks 
第11週
 12/02  Distributed Representations for Natural Languages 
第12週
 12/09  Regularizations and Optimizations 
第13週
 12/16  Convolutional Network, Part 1 
第14週
 12/23  Convolutional Network, Part 2 
第15週
 12/30  Final Project Presentation 
第16週
 1/06  TBD