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 357302 Artificial intelligence development and security 1 3.0 3 ★ TSUI PENG GIFM
MSIS 32 0 資財四甲、資財所和創新資安合開

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Spring Semester Year 2026	357302	Artificial intelligence development and security	1	3.0	3	★	TSUI PENG	GIFM MSIS	32	0	資財四甲、資財所和創新資安合開

Course Plan：

Instructor TSUI PENG　Office Hours

Email johnpeng@mail.ntut.edu.tw

Last Updated 2025-12-19 16:09:43

Course Objective 本課程旨在介紹人工智慧（AI）領域包含各種機器學習的開發與實作，特別關注如何使用Python進行模型的開發與部屬。課程將涵蓋深度學習的基本概念、常見的AI框架（如TensorFlow、Keras），並深入探討如何利用Python編程語言來設計、訓練與優化AI模型。此外，課程也將重點討論人工智慧在開發與部屬過程中需要考量的安全性問題，從資料安全與可稽核性，AI透明度，模型加密與攻擊防範等，提供學生一套全面的安全檢核框架。學生將學習如何確保AI系統在實際應用中具備高度的安全性與可靠性，並瞭解如何在AI部屬的不同階段識別與解決潛在的安全風險。 This course aims to introduce the development and implementation of various machine learning techniques in the field of Artificial Intelligence (AI), with a particular focus on how to use Python for model development and deployment. The course will cover the fundamental concepts of deep learning, popular AI frameworks (such as TensorFlow and Keras), and will delve into how to use the Python programming language to design, train, and optimize AI models. Additionally, the course will emphasize the security considerations necessary during the development and deployment of AI systems, including data security and auditability, AI transparency, model encryption, and attack prevention. Students will be provided with a comprehensive security framework to evaluate these concerns. They will also learn how to ensure the high security and reliability of AI systems in practical applications, and how to identify and mitigate potential security risks at various stages of AI deployment.

Course Schedule Week 1: Introduction Week 2: Python review Week 3: ML data processing Week 4: Supervised learning algorithm Week 5: Unsupervised learning algorithm Week 6: NN Basic and PBL project Week 7: Forward propagation and Back propagation Week 8: CNN and Dataset Week 9: Mid-term Week 10:　RNN & LSTM Week 11-13: Generative AI Week 14: Reinforcement Learning Week 15,16 AI DevOPS Security Week 17 & 18 Final Term

Evaluation and grading policy • Homework, class participation: 30% • Midterm report & presentation: 30% • Final project: 40%

Materials All right reserved. Do not reproduce without permission.

Foreign-language textbooks:Yes
Google ML Course : https://developers.google.com/machine-learning Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow (3nd Ed.)

The access to curricular consultation johnpeng@mail.ntut.edu.tw

The course website will be listed on
https://tipeng.wixsite.com/school/

The course corresponds to the SDGs SDG4：優質教育（Quality Education）
SDG9：產業創新與基礎設施（Industry, Innovation and Infrastructure）

Does the course incorporate AI ● 深入探討AI的原理與應用（Explore the principles and applications of AI in depth）

Note
　

Instructor	TSUI PENG　Office Hours
Email	johnpeng@mail.ntut.edu.tw
Last Updated	2025-12-19 16:09:43
Course Objective	本課程旨在介紹人工智慧（AI）領域包含各種機器學習的開發與實作，特別關注如何使用Python進行模型的開發與部屬。課程將涵蓋深度學習的基本概念、常見的AI框架（如TensorFlow、Keras），並深入探討如何利用Python編程語言來設計、訓練與優化AI模型。此外，課程也將重點討論人工智慧在開發與部屬過程中需要考量的安全性問題，從資料安全與可稽核性，AI透明度，模型加密與攻擊防範等，提供學生一套全面的安全檢核框架。學生將學習如何確保AI系統在實際應用中具備高度的安全性與可靠性，並瞭解如何在AI部屬的不同階段識別與解決潛在的安全風險。 This course aims to introduce the development and implementation of various machine learning techniques in the field of Artificial Intelligence (AI), with a particular focus on how to use Python for model development and deployment. The course will cover the fundamental concepts of deep learning, popular AI frameworks (such as TensorFlow and Keras), and will delve into how to use the Python programming language to design, train, and optimize AI models. Additionally, the course will emphasize the security considerations necessary during the development and deployment of AI systems, including data security and auditability, AI transparency, model encryption, and attack prevention. Students will be provided with a comprehensive security framework to evaluate these concerns. They will also learn how to ensure the high security and reliability of AI systems in practical applications, and how to identify and mitigate potential security risks at various stages of AI deployment.
Course Schedule	Week 1: Introduction Week 2: Python review Week 3: ML data processing Week 4: Supervised learning algorithm Week 5: Unsupervised learning algorithm Week 6: NN Basic and PBL project Week 7: Forward propagation and Back propagation Week 8: CNN and Dataset Week 9: Mid-term Week 10:　RNN & LSTM Week 11-13: Generative AI Week 14: Reinforcement Learning Week 15,16 AI DevOPS Security Week 17 & 18 Final Term
Evaluation and grading policy	• Homework, class participation: 30% • Midterm report & presentation: 30% • Final project: 40%
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:Yes Google ML Course : https://developers.google.com/machine-learning Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow (3nd Ed.)
The access to curricular consultation	johnpeng@mail.ntut.edu.tw The course website will be listed on https://tipeng.wixsite.com/school/
The course corresponds to the SDGs	SDG4：優質教育（Quality Education） SDG9：產業創新與基礎設施（Industry, Innovation and Infrastructure）
Does the course incorporate AI	● 深入探討AI的原理與應用（Explore the principles and applications of AI in depth）
Note