Course Syllabus

Course Information：

Year-Semester Course Number Course Name Phase Credits Hours Required/Elective Instructor Class Student NO. Withdraw Note

Spring Semester
Year 2026 360352 Interdisciplinary Project in Artificial Intelligence Applications 1 3.0 3 ★ YU-CHENG FAN
Peng-Chun Peng
Hsin-Han Chiang AI雙聯專班 15 0 3/22.28; 4/18; 5/9.16.30

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Spring Semester Year 2026	360352	Interdisciplinary Project in Artificial Intelligence Applications	1	3.0	3	★	YU-CHENG FAN Peng-Chun Peng Hsin-Han Chiang	AI雙聯專班	15	0	3/22.28; 4/18; 5/9.16.30

Course Plan：

Instructor Peng-Chun Peng　Office Hours

Email pcpeng@ntut.edu.tw

Last Updated 2026-03-17 23:47:26

Course Objective This course is based on the management problems that students encounter at work, including operations research (OR), production planning and management, financial analysis, etc., and explores the technical principles of using machine learning, as well as the feasibility and scalability of application in these fields. The discussion scope of the machine learning will not only cover the most basic concepts and principles of convolutional neural networks (CNN), self-attention, transformer, generative model, large language models (LLM), linear programming, and probabilistic programming, but also guide students to understand the importance of one or more of these architectures. In terms of teaching aids, in line with current trends, the programming development environment will be combined with an LLM approach to make it easier for students to quickly get started with programming languages. While looking at their own examples to achieve their own results, they will have a higher sense of accomplishment. The students can also accept the meaning of LLM’s most popular prompt engineering and parameter quantities. In addition, we will discuss some AI case studies, including applications of AI in medical, verbal communication, autonomous driving, education, and in multiple fields. Students will be able to apply AI technology to various fields.

Course Schedule This course uses a problem-based learning (PBL) approach to tackle real-world business issues, guiding students through interdisciplinary AI projects. It aims to teach students to apply AI technologies, such as machine learning, image recognition, and natural language processing, across domains including data analysis, healthcare, and smart manufacturing. Students will gain practical skills, enhance problem-solving abilities, and develop innovative thinking. The course prepares students to handle AI projects, understand industry challenges, and cultivate entrepreneurial and innovative spirits. Basic knowledge: A. History and Origin of OR B. Basic concepts of production planning and control C. Financial Management and Quantitative Science D. Differences and discussions between basic probability and statistics and Bayesian statistics E. Models of artificial intelligence Tools and Techniques: A. Programming language B. LLM prompt engineering and common prompts C. Google Colaboratory and Gemini D. How to analyze and preprocess the data form and content given to the computer

Evaluation and grading policy Based on a comprehensive score of class attendance and course participation.

Materials All right reserved. Do not reproduce without permission.

Foreign-language textbooks:Yes
1. Frederick S. Hillier, Gerald J. Lieberman, “Introduction to Operations Research” 2. Stephen N. Chapman, “The fundamentals of production planning and control” 3. QuantInsti Quantitative Learning Pvt. Ltd., “Python Basics with Illustrations from the Financial Markets” 4. Other related documents and briefings are provided at separate download URLs.

The access to curricular consultation email

Expanding teaching and resources ● 數位教材資源應用 (Application of Digital Resources)
採用影音多媒體或具開放授權之資源（如OCW、開放教科書）作為主要或輔助教材。
Adopts multimedia or open-licensed resources (e.g., OCW, Open Textbooks) as primary or supplementary teaching materials.

The course corresponds to the SDGs SDG4：優質教育（Quality Education）

Does the course incorporate AI ● 鼓勵學生使用生成式AI工具（Encourage students to use generative AI tools）

Note
　

Instructor	Peng-Chun Peng　Office Hours
Email	pcpeng@ntut.edu.tw
Last Updated	2026-03-17 23:47:26
Course Objective	This course is based on the management problems that students encounter at work, including operations research (OR), production planning and management, financial analysis, etc., and explores the technical principles of using machine learning, as well as the feasibility and scalability of application in these fields. The discussion scope of the machine learning will not only cover the most basic concepts and principles of convolutional neural networks (CNN), self-attention, transformer, generative model, large language models (LLM), linear programming, and probabilistic programming, but also guide students to understand the importance of one or more of these architectures. In terms of teaching aids, in line with current trends, the programming development environment will be combined with an LLM approach to make it easier for students to quickly get started with programming languages. While looking at their own examples to achieve their own results, they will have a higher sense of accomplishment. The students can also accept the meaning of LLM’s most popular prompt engineering and parameter quantities. In addition, we will discuss some AI case studies, including applications of AI in medical, verbal communication, autonomous driving, education, and in multiple fields. Students will be able to apply AI technology to various fields.
Course Schedule	This course uses a problem-based learning (PBL) approach to tackle real-world business issues, guiding students through interdisciplinary AI projects. It aims to teach students to apply AI technologies, such as machine learning, image recognition, and natural language processing, across domains including data analysis, healthcare, and smart manufacturing. Students will gain practical skills, enhance problem-solving abilities, and develop innovative thinking. The course prepares students to handle AI projects, understand industry challenges, and cultivate entrepreneurial and innovative spirits. Basic knowledge: A. History and Origin of OR B. Basic concepts of production planning and control C. Financial Management and Quantitative Science D. Differences and discussions between basic probability and statistics and Bayesian statistics E. Models of artificial intelligence Tools and Techniques: A. Programming language B. LLM prompt engineering and common prompts C. Google Colaboratory and Gemini D. How to analyze and preprocess the data form and content given to the computer
Evaluation and grading policy	Based on a comprehensive score of class attendance and course participation.
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:Yes 1. Frederick S. Hillier, Gerald J. Lieberman, “Introduction to Operations Research” 2. Stephen N. Chapman, “The fundamentals of production planning and control” 3. QuantInsti Quantitative Learning Pvt. Ltd., “Python Basics with Illustrations from the Financial Markets” 4. Other related documents and briefings are provided at separate download URLs.
The access to curricular consultation	email
Expanding teaching and resources	● 數位教材資源應用 (Application of Digital Resources) 採用影音多媒體或具開放授權之資源（如OCW、開放教科書）作為主要或輔助教材。 Adopts multimedia or open-licensed resources (e.g., OCW, Open Textbooks) as primary or supplementary teaching materials.
The course corresponds to the SDGs	SDG4：優質教育（Quality Education）
Does the course incorporate AI	● 鼓勵學生使用生成式AI工具（Encourage students to use generative AI tools）
Note