教學大綱與進度

課程基本資料：

學年期	課號	課程名稱	階段	學分	時數	修	教師	班級	人	撤	備註
111-1	306996	人工智慧	1	3.0	3	★	林郁修	自動化所 機電博所 機電外國學生專班	23	1	電腦教室,自動化所、機電博班(含外生班)合開

教學大綱與進度：

教師姓名	林郁修　教師諮商時間(Office Hours)
Email	yhlin@ntut.edu.tw
最後更新時間	2022-05-26 19:20:30
課程大綱	This semester's Artificial Intelligence (AI) course will focus on Machine Learning (ML) and Deep Learning (DL) in data science analytics. We will look at supervised and unsupervised learning methods, which will include classic Multi-Layer Perceptron (MLP), Deep Neural Networks/Convolutional Neural Networks (CNN), and k-Means clustering. This course is designed for graduate students who are interested in AI and its applications in data science analytics. Students who take this course should have mathematical maturity of undergraduate curricula in science and engineering, including Calculus, Discrete Mathematics, Linear Algebra and programming language such as C/C++/MATLAB/Python. Teaching approaches conducted in this course emphasize analysis, modeling and design principles of AI methodology. Case studies, engineering applications of AI in data science analytics, will also be covered in this course. Collaboration Policy: You are free to form study groups and discuss programming assignments and projects. However, you must write up assignments and code independently, and you must acknowledge in your submission all the students you discussed with.
課程進度	Week Topic 1 Introduction to IoT/AI/ML/DL (Overview of this course) 2 Foundations for ML (Remote Learning) 3 Supervised learning (I) -- Perceptron (Programming assignment #1) 4 Supervised learning (II) -- Multi-Layer Perceptron (MLP) 5 Programming assignment #1 (Oral / Programming assignment #1 Due) 6 Supervised learning (III) -- MLP (scikit-learn) 7 Supervised learning (IV) -- MLP (scikit-learn) (Programming assignment #2) 8 Programming assignment #2 (Oral / Programming assignment #2 Due) 9 Mid-term exam 10 Un-supervised learning -- k-Means clustering (scikit-learn) 11 Foundations for DL 12 Supervised learning (I) -- Deep Neural Networks (TensorFlow) 13 Supervised learning (II) -- Convolutional Neural Networks (CNN) 14 Supervised learning (III) -- CNN (TensorFlow/Keras) 15 Supervised learning (IV) -- CNN (TensorFlow/Keras) (Programming assignment #3) 16 Programming assignment #3 (Oral / Programming assignment #3 Due) 17 Final report (Term-project report or Paper reading report) (Oral) (Remote Learning) 18 Final report (Oral / Final report (PPT) Due) A free, on-line course "Getting Started with AI on Jetson Nano (https://courses.nvidia.com/courses/course-v1:DLI+S-RX-02+V2/about)" from " NVIDIA Deep Learning Institute" may be included in this semester's AI course.
評量方式與標準	- Class participation: 15% - Assignments: 30% (Three programming assignments: No assignment turned in late will be accepted) - Mid-term exam: 30% - Final report: 25%
使用教材、參考書目或其他	【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】 使用外文原文書：是 Course lectures will be distributed through our University's iStudy+ (e-learning) system.
課程諮詢管道	e-mail: yhlin@ntut.edu.tw LINE : this course's LINE group (will be announced)
備註	Remote Learning will be performed via Microsoft Teams, if required (see https://news.ntut.edu.tw/p/422-1000-1085.php?Lang=zh-tw).