本課程教學大綱已提供完整英文資訊(本選項僅供統計使用,未提供完整英文資訊者,得免勾記)【Provide information of course syllabus in English.(This is for statistical use only. For those who do not provide information of course syllabus in English, do not check this field.)】
*** 本課程採「同步遠距含錄影」上課,課程與連線相關資訊將置於本校網路大學課程頁面, 請至本校圖資處首頁網路大學登入*** *** 未選上課無法登入的同學,第一堂課上課請至 https://meet.google.com/yhq-eada-jrs *** *** 本課程與 「CM 503- 大數據分析、機器學習、與人工智慧方法」併班上課 *** Students will be introduced to theories & techniques in different fields related to AI, including probability & statistics, scientific computing, data engineering, algorithm design, statistical learning, deep learning, and explainable AI. Prerequisite: Basic understanding of relational databases, SQL, data structures, probability & statistics, college-level calculus, and matrix operations are required. Familiar with at least one high-level programming language. Scientific programming language, such as R, Matlab, Python, Scala, Julia, and SAS are preferred. Students who have taken CM502 are welcomed.
課程目標 Objectives
This course is designed for students who need hands-on training of data engineering, machine learning, and general understanding of AI. We will begin with introduction to the rise and evolution of the Data Science. Its applications in various fields, such as business, healthcare, insurance, and finance, will also be discussed. This course covers the basic concepts of Big Data Analytics, Data Engineering, Business Analytics, MapReduce Design Patterns, Supervised & Unsupervised Machine Learning, in-memory computing, Functional Programming, Deep Neural Networks, and Machine Learning Interpretability. Students will also be introduced to how to use R & Python programming language and its packages to solve real-world big data problems.
授課方式 Teaching methods
1. Onsite & online video lectures 2. In-class quiz
參考書/教科書/閱讀文獻 Reference book/ textbook/ documents
〔請遵守智慧財產權觀念,不可非法影印。教師所提供之教材供學生本人自修學習使用,不得散播及做為商業用途〕
No copies for intellectual property rights. Textbooks provided by the instructor used only for self-study, can not broadcast or commercial use
* G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning: with Applications in R, 2nd Edition, Springer (Available free online: https://www.statlearning.com/) * F. Buisson, Behavioral Data Analysis with R and Python. O’Reilly Media, Inc., 2021. * K. Hwang and M. Chen, Big-Data Analytics for Cloud, IoT and Cognitive Computing, 1st ed. Wiley Publishing, 2017. * EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data. John Wiley & Sons, 2015. * N. Matloff, The Art of R Programming: A Tour of Statistical Software Design, 1st edition. No Starch Press, 2011. * Kabacoff, Robert. R in Action. Manning Publications Co., 2011 * C. O'Neil and R. Schutt, Doing Data Science: Straight Talk from the Frontline, 1st edition. O'Reilly Media, 2013. * F. Chollet and J. J. Allaire, Deep Learning with R, 1 edition. Manning Publications, 2018. * A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O’Reilly Media, Inc., 2019. * W. McKinney, Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython. O’Reilly Media, Inc., 2017. * F. Provost, T. Fawcett. Data Science for Business: What you need to know about data mining and data-analytic thinking, O'Reilly Media, Inc., 2013. * C. Molnar, Interpretable Machine Learning: A Guide For Making Black Box Models Explainable. Munich, Germany: Independently published, 2022. (https://christophm.github.io/interpretable-ml-book/) * J. Pearl, M. Glymour, and N. P. Jewell, Causal Inference in Statistics - A Primer, 1st edition. Chichester, West Sussex: Wiley, 2016.
彈性暨自主學習規劃 Alternative learning periods
本門課程是否有規劃實施學生彈性或自主學習內容(每1學分2小時)
Is any alternative learning periods planned for this course (with each credit corresponding to two hours of activity)?
否:教師需於「每週課程內容及預計進度」填寫18週課程進度(每1學分18小時之正課內容)。 No:The instructor will include an 18-week course plan in the weekly scheduled progress (each credit corresponds to 18 hours of instruction)
是:教師需於「每週課程內容及預計進度」填寫16週課程內容(每1學分16小時之正課內容),並於下列欄位填寫每1學分2小時學生彈性或自主學習內容。 Yes:The instructor will include a 16-week course plan in the weekly scheduled progress (each credit corresponds to 16 hours of instruction);the details of the planned alternative learning periods are provided below (each credit corresponds to two hours of activity).
學生彈性或自主學習活動 Alternative learning periods
勾選或填寫規劃內容 Place a check in the appropriate box or provide details
時數 Number of hours
學生分組實作及討論 Group work and discussion
參與課程相關作業、作品、實驗 Participation in course-related assignments, work, or experiments
參與校內外活動(研習營、工作坊、參訪)或競賽 Participation in on- or off-campus activities (e.g., seminars, workshops, and visits) or competitions
課外閱讀 Extracurricular reading
線上數位教材學習 Learning with online digital learning materials
其他(請填寫規劃內容) Other (please provide details)
每週課程內容及預計進度 Weekly scheduled progress
週次
日期
授課內容及主題
Week
Date
Content and topic
1
2022/09/04~2022/09/10
Course Introduction
2
2022/09/11~2022/09/17
Introduction to Data Engineering — I
3
2022/09/18~2022/09/24
Introduction to Data Engineering — II
4
2022/09/25~2022/10/01
Introduction to Data Engineering — III
5
2022/10/02~2022/10/08
Fundamentals of Data Analytics — I
6
2022/10/09~2022/10/15
Fundamentals of Data Analytics — II
7
2022/10/16~2022/10/22
Fundamentals of Data Analytics — III
8
2022/10/23~2022/10/29
Introduction to Statistical Learning — I
9
2022/10/30~2022/11/05
Project Proposal Defense — I
10
2022/11/06~2022/11/12
Project Proposal Defense — II
11
2022/11/13~2022/11/19
Introduction to Statistical Learning — II
12
2022/11/20~2022/11/26
Supervised Learning — Regression
13
2022/11/27~2022/12/03
Supervised Learning — Classification
14
2022/12/04~2022/12/10
Topics in Unsupervised Learning
15
2022/12/11~2022/12/17
Topics in Interpretable Machine Learning
16
2022/12/18~2022/12/24
Topics in Causal Inference
17
2022/12/25~2022/12/31
Term Project Presentation — I
18
2023/01/01~2023/01/07
Term Project Presentation — II
課業討論時間 Office hours
時段1 Time period 1: 時間 Time:星期一10am-12pm 地點 Office/Laboratory:By appointment 時段2 Time period 2: 時間 Time:星期三10am-12pm 地點 Office/Laboratory:By appointment
系所學生專業能力/全校學生基本素養與核心能力 basic disciplines and core capabilitics of the dcpartment and the university
系所學生專業能力/全校學生基本素養與核心能力 basic disciplines and core capabilities of the department and the university
課堂活動與評量方式 Class activities and evaluation
本課程欲培養之能力與素養 This course enables students to achieve.
紙筆考試或測驗 Test.
課堂討論︵含個案討論︶ Group discussion (case analysis).
個人書面報告、作業、作品、實驗 Indivisual paper report/ assignment/ work or experiment.
群組書面報告、作業、作品、實驗 Group paper report/ assignment/ work or experiment.
個人口頭報告 Indivisual oral presentation.
群組口頭報告 Group oral presentation.
課程規劃之校外參訪及實習 Off-campus visit and intership.
證照/檢定 License.
參與課程規劃之校內外活動及競賽 Participate in off-campus/ on-campus activities and competitions.
課外閱讀 Outside reading.
※系所學生專業能力 Basic disciplines and core capabilities of the department
1.具備資訊倫理與社會責任實踐的能力 1. Awareness of information ethics.
2.具備溝通能力 2. Communication Skills.
3.具備解決資訊管理問題之能力 3. Capabilities to solve IT-related problems.
4.具備資訊管理之專業知識 4. Professional knowledge of information technology.
5.具備國際觀 5. Global perspective.
※全校學生基本素養與核心能力 Basic disciplines and core capabilities of the university
1.表達與溝通能力。 1. Articulation and communication skills
2.探究與批判思考能力。 2. Inquisitive and critical thinking abilities
3.終身學習能力。 3. Lifelong learning
4.倫理與社會責任。 4. Ethnics and social responsibility
5.美感品味。 5. Aesthetic appreciation
6.創造力。 6. Creativity
7.全球視野。 7. Global perspective
8.合作與領導能力。 8. Team work and leadership
9.山海胸襟與自然情懷。 9. Broad-mindedness and the embrace of nature
Internship: The required or elective courses should include credits and learning hours. Students should participate in the corporative company or institution to practice and learn the real skills. An internship certification must be handed in at the end of internship to get the credits or to fulfil the graduation requirements.