Course Syllabus

Course Information：

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Fall Semester Year 2025	352118	Scientific Visualization	1	3.0	3	★	Yuan-Sen Yang	GCDPE	15	0	土木208

Course Plan：

Instructor	Yuan-Sen Yang　Office Hours
Email	ysyang@ntut.edu.tw
Last Updated	2025-06-02 14:42:26
Course Objective	This course covers the theory and practice of scientific visualization, which is the graphical process of creating effective visual representations of 2D and 3D scientific data sets. The course will teach students the techniques and tools for generating, manipulating, analyzing and displaying various types of data, such as scalar fields, vector fields, and images. The course will also introduce some topics related to machine learning and graphical processing unit (GPU). Due to AI technology, the way of writing programs is changing significantly. This course teaches students how to develop programs using AI technology and how to use techniques to effectively communicate with AI to complete multi-file project-based program development. By the end of this course, students should be able to: 1. Use AI tool(s) to develop software. Learn skills to efficiently communicate with AI for generating programming code and multi-file software projects. 2. Apply appropriate visualization techniques for different types of data 3. Use existing visualization software packages and libraries, including Python Matplotlib and Matlab. 4. Describe the current technical relationship between GPU, image processing, and machine learning.
Course Schedule	W1. Introduction to scientific visualization W2. Visualization and data animation in Python using Matplotlib W3. Take-home exercise of Python and Matplotlib W4. Basic computer vision machine learning W5. Memory layout of arrays in Numpy W6. Midterm W7. Convolution and its hands-on exercise using Python and Numpy W8. The MNIST problem and CNN refinement for the MNIST problem W9. CNN parameters explanation, overfitting, and some solutions W10. Data augmentation and callback functions W11. Transfer learning and hands-on exercise W12. Image segmentation and hands-on exercise W13. Image segmentation and hands-on exercise (ii) W14. Image segmentation and hands-on exercise (iii) W15. Generative Adversarial Network and generative AI W16: GPU for computer graphics and computer vision W17: Parallel computing on CPUs and GPUs W18. Project presentations
Evaluation and grading policy	1. Lecture activities (attendance, interaction, lecture assistance) (20% +/- 5%) 2. Midterm (20% +/- 5%) 3: Final Presentation: in classroom (25% +/- 5%) 4: Final Presentation: as a Youtuber (35% +/- 5%)
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:Yes - The Visualization Toolkit: An Object-Oriented Approach to 3D Graphics by William Schroeder and Ken Martin - Matplotlib official website: https://matplotlib.org/ - Matlab visualization official website: https://www.mathworks.com/products/matlab/matlab-graphics.html#visualize_data
The access to curricular consultation	To be annouced
Expanding teaching and resources
The course corresponds to the SDGs	SDG4：優質教育（Quality Education）
Does the course incorporate AI	● 使用生成式AI作為教學過程的輔助工具（Use generative AI tools as an aid to the teaching process） ● 鼓勵學生使用生成式AI工具（Encourage students to use generative AI tools） ● 使用生成式AI進行課堂即時互動（Use generative AI for real-time classroom interaction） ● 簡單介紹AI的基本概念（Briefly introduce the basic concept of AI）
Note	The lecture is regularly video recorded and is available at the NTUT iStudy (北科 i 學園). In case that the lecture has to be carried out online, it will be at Google Meet: https://meet.google.com/yiu-jwqa-ckm