課程資訊
課程名稱
機器學習與深度學習導論
Introduction to Machine Learning and Deep Learning 
開課學期
112-1 
授課對象
工學院  土木工程學研究所  
授課教師
陳俊杉 
課號
CIE5133 
課程識別碼
521 U9230 
班次
 
學分
3.0 
全/半年
半年 
必/選修
選修 
上課時間
星期三2,3,4(9:10~12:10) 
上課地點
新505 
備註
第一堂課以抽籤方式決定修課名單。
總人數上限:80人 
 
課程簡介影片
 
核心能力關聯
本課程尚未建立核心能力關連
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 is an introductory course to machine learning and deep learning (short for ML) offered by the Department of Civil Engineering, National Taiwan University. Artificial intelligence, in particular the ML subfield, is now ubiquitous. Using data as its core, the rapid surge and democratization on ML accelerates innovation in many domains. It is thus essential for students with engineering background to acquire basic understanding and ability on the subject.

This course is designed to help you to view problems and applications from a ML perspective and to understand principles of ML. There is a fundamental structure to ML thinking and basic principles that should be understood. There are also particular areas where intuition, creativity, common sense, and domain knowledge must be brought to bear. A ML perspective aims to provide students with structure and principles, and this will give you a framework to systematically analyze problems and to develop applications in various domains. 

課程目標
The objective of this course is to provide you with fundamental understanding of ML and with how to apply ML theories and techniques to analyze applications with data. To comprehend the contents, you will need working knowledge on elementary Engineering Mathematics.

This course will also emphasize on hand-on experience of doing ML via Python. You need to be familiar with the basic of Python and are willing to learn more. You are advised to take at least one solid introductory course on Python (for example, my freshman Python course) before taking this course.

After taking this course, you should be able to: (1) approach problems and applications with ML in mind, (2) understand fundamental principles of ML and (3) use Python to process data and do ML. 
課程要求
1. working knowledge on elementary Engineering Mathematics
2. familiar with the basic of Python and are willing to learn more. 
預期每週課後學習時數
 
Office Hours
 
指定閱讀
 
參考書目
Principles, Theories and Algorithms
1. James, G., Witten, D., Hastie, T., Tibshirani, R. (2013), An Introduction to Statistical Learning.
2. Tan, P. N., Steinbach M., Karpatne A., Kumar V. (2018), Introduction to Data Mining, Second Edition.
3. Abu-Mostafa, Y S, Magdon-Ismail, M., Lin, H-T (2012) Learning from Data, AMLbook.com.
4. Bishop, C (2006) Pattern Recognition and Machine Learning, Springer.
5. Goodfellow, I., Bengio, Y., Courville, A., Bach, F. (2016) Deep Learning, MIT Press.

Python Programming
1. Jake VanderPlas (2016), A Whirlwind Tour of Python, O'Reilly (freely available from http://www.oreilly.com/programming/free/files/a-whirlwind-tour-of-python.pdf)
2. Jake VanderPlas (2016), Python Data Science Handbook, O'Reilly. (online version freely available from https://jakevdp.github.io/PythonDataScienceHandbook)
3. Francois Chollet (2016), Deep Learning with Python, Manning Publications. (Second Edition is underway) 
評量方式
(僅供參考)
   
課程進度
週次
日期
單元主題
無資料