Artificial Intelligence and Advanced Nanotechnology [3]

課程名稱 Course Title	人工智慧與奈米科技 Artificial Intelligence and Advanced Nanotechnology
開課學期 Semester	114-2 (2026 Spring)
開課系所 Department	TIGP奈米學程
授課教師 Lecturer	Chun-Wei Pao
班次 Class
學分 Credits	3
全/半年 Full/Half Yr.	Half Yr.
必/選修 Required/ Elective	Elective
上課時間 Schedule	Friday 14:10-17:00
上課地點 Classroom	中研院跨領域大樓 C101, Interdisciplinary Research Building for Science and Technology, AS (3/6.3/20.4/24.5/22 -4B05, Interdisciplinary Research Building for Science and Technology, AS)
課程大綱 Course Syllabus
課程概述 Course Description	This graduate course introduces modern machine learning for advanced nanotechnology, including nanomaterials and nanobiotechnology, designed for STEM students without an EE/CS background. The course will build core intuition for neural networks, convolutional models, Transformers, and generative approaches (GANs, diffusion), and then pivot to applications in materials simulation (graph neural networks and machine‑learned interatomic potentials), materials discovery, and the principles behind autonomous, closed‑loop experimentation. Guest mini‑modules covering biomedical imaging modeling and data‑driven drug discovery will be included. Emphasis is on concepts, seminal papers, and scientific decision‑making rather than coding.
課程目標 Course Objective	By the end of the course, students will be able to interpret and critique foundational ML papers; explain when and why to use CNNs, Transformers, and generative models; frame materials property prediction and inverse‑design problems; reason about accuracy, data efficiency, uncertainty, and constraints in scientific workflows; and outline the architecture of a self‑driving laboratory. Students will also gain a high‑level understanding of biomedical imaging pipelines and molecular modeling workflows and how these connect to materials discovery.
課程要求 Course Requirement	Prerequisites: undergraduate‑level calculus, linear algebra, and probability/statistics; a STEM background. Prior programming experience is helpful but not required; minimal familiarity with Python is recommended
評量方式 Evaluation	Homeworks (60%), project (40%)