NCHU Course Outline
Course Name (中) 人工智慧應用在教育數據(一)(5916)
(Eng.) Fundamentals for AI Applications in Educational Data (I)
Offering Dept Graduate Institute of Data Science and Information Computing
Course Type Elective Credits 1 Teacher Hao-Chiang Shao
Department General Language Chinese 英文/EMI Semester 2025-FALL
Course Description 以橋接教育資料分析與傳統機器學習為主要目標，對相關議題所需的基礎數學理論為主要授課材料。基礎理論介紹將涵蓋但不限於：線性代數、訊息理論、數位信號處理(1維時間序列分析)、multi-dimensional scaling、社群網路分析等議題。
Prerequisites
self-directed learning in the course Y
Relevance of Course Objectives and Core Learning Outcomes(%) Teaching and Assessment Methods for Course Objectives
Course Objectives Competency Indicators Ratio(%) Teaching Methods Assessment Methods
1、 了解教育大數據分析所需的基礎數學知識
1.
2.
3.
5.
6.
20
20
20
20
20
Lecturing
Assignment
Quiz
Course Content and Homework/Schedule/Tests Schedule
Week Course Content
Week 1 Introduction to Artificial Intelligence and Machine Learning.
(Problem formulation, modeling, introduction to common commercial software and open datasets, reference and textbooks)
Week 2 Introduction to Artificial Intelligence and Machine Learning.
(Problem formulation, modeling, introduction to common commercial software and open datasets, reference and textbooks)
Week 3 Introduction to Artificial Intelligence and Machine Learning.
(Problem formulation, modeling, introduction to common commercial software and open datasets, reference and textbooks)
Week 4 Mathematical basics- I
(Linear Algebra, Information Theory, Probability)
Week 5 Mathematical basics- I
(Linear Algebra, Information Theory, Probability)
Week 6 Mathematical basics- I
(Linear Algebra, Information Theory, Probability)
Week 7 Mathematical basics- II
(Deep neural network basics)
Week 8 Mathematical basics- II
(Deep neural network basics)
Week 9 Mathematical basics- II
(Deep neural network basics)
Week 10 Mathematical basics- III
(Typical loss function designs)
Week 11 Mathematical basics- III
(Typical loss function designs)
Week 12 Mathematical basics- III
(Typical loss function designs)
Week 13 Mathematical basics- IV
(Advanced neural networks-1)
Week 14 Mathematical basics- IV
(Advanced neural networks-1)
Week 15 Mathematical basics- IV
(Advanced neural networks-1)
Week 16 Mathematical basics- V
(Advanced neural networks-2) Mathematical basics- V
(Advanced neural networks-2) Mathematical basics- V
(Advanced neural networks-2)
self-directed
learning
Evaluation
作業100%
Textbook & other References
Oppenheim et al. ”Digital Signal Processing”
Newman, ”Networks: an introduction”
Cover and Thomas, ”Elements of Information Theory”
Other papers
Teaching Aids & Teacher's Website

Office Hours
Wed. afternoon 1500~1600
Sustainable Development Goals, SDGs(Link URL)
include experience courses：N
Please respect the intellectual property rights and use the materials legally.Please respect gender equality.
Update Date, year/month/day：None Printed Date, year/month/day：2025 / 7 / 02
The second-hand book website：http://www.myub.com.tw/