{"course":{"id":"109112800D01","name":"人工智慧","enroll_type":"選修","general_type":"","dept":"電機系碩士班","grade":1,"class_group":"甲","teacher":"林郁修","credit":3,"hour":3,"time":[{"day":4,"section":[2,3,4]}],"classroom":"","max":30,"min":5,"remark":"","alt_for":"","courses":""},"detail":[["指定教材","Satish Kumar, Neural Networks : A Classroom Approach, 2/e (Paperback), McGraw-Hill Education, 2013."],["參考教材","Lectures will be distributed through our University's e-learning system. The referenced textbooks in this course include: 1. Yaser S. Abu-Mostafa,\nMalik Magdon-Ismail, and Hsuan-Tien Lin, Learning From Data, AMLBook, 2012. 2. Chin-Teng Lin and C. S. George Lee, Neural Fuzzy Systems: A NeuroFuzzy Synergism to Intelligent Systems, Prentice Hall, 1996."],["成績評量標準","- Class participation: 15% - Assignments: 30% (Three programming assignments: No assignment turned in late will be accepted.) - Mid-term\nexam: 30% - Term-project report: 25 % (The term-/final project provides an opportunity for you to use tools/principles and techniques from class to build\nsomething interesting of your choice. Projects should be done in groups of up to four.)"],["教學方法","理論講授,實務講授,個人實驗(實作),其他"],["教學目標","This semester's Artificial Intelligence (AI) course will focus on Machine Learning (ML) with related work in data science analytics/Smart Grid. We\nwill look at classic supervised and un-supervised learning methods, which will include looking at linear regression, Perceptron/Multi-Layer Perceptron (MLP),\nk-Means clustering and optimization techniques such as Genetic Algorithms (GA). This course is designed for graduate students who are interested in AI and its\napplications in Smart Grid. Students who take this course should have mathematical maturity of undergraduate curricula in science and engineering, including\nCalculus, Discrete Mathematics, Linear Algebra and programming language such as C/C++/MATLAB/Python. Teaching approaches conducted in this course\nemphasize analysis, modeling and design principles of AI methodology. Case studies including engineering applications of AI in Smart Grid will also be\ncovered in this course. Collaboration Policy & Honor Code: You are free to form study groups and discuss assignments and projects. However, you must write\nup assignments and code from scratch independently, and you must acknowledge in your submission all the students you discussed with. Honor code violations:\nLooking at the writeup or code of another student & Showing your writeup or code to another student."]],"office_time":[["林郁修","(三)13:00~17:00"]],"schedule":[["2020/09/17","2","4","3","林郁修","Introduction to IoT/AI/ML/Smart Grid","","","Overview of this course"],["2020/09/24","2","4","3","林郁修","Python (I)","","",""],["2020/10/01","2","4","3","林郁修","Python (II)","","",""],["2020/10/08","2","4","3","林郁修","Foundations for ML","","",""],["2020/10/15","2","4","3","林郁修","Regression & Classification","","",""],["2020/10/22","2","4","3","林郁修","Supervised learning (I)","Programming assignment #1","Perceptron",""],["2020/10/29","2","4","3","林郁修","Supervised learning (II)","","Multi-Layer Perceptron",""],["2020/11/05","2","4","3","林郁修","Supervised learning (II)","Programming assignment #2","Multi-Layer Perceptron","Programming assignment #1 Due"],["2020/11/12","2","4","3","林郁修","Mid-term exam","","",""],["2020/11/19","2","4","3","林郁修","Un-supervised learning","","k-Means clustering","Programming assignment #2 Due"],["2020/11/26","2","4","3","林郁修","Evolutionary computing (I)","","Genetic Algorithms",""],["2020/12/03","2","4","3","林郁修","Evolutionary computing (II)","Programming assignment #3","Genetic Algorithms",""],["2020/12/10","2","4","3","林郁修","Case Study","","",""],["2020/12/17","2","4","3","林郁修","Case Study","","","Programming assignment #3 Due"],["2020/12/24","2","4","3","林郁修","Case Study","","",""],["2020/12/31","2","4","3","林郁修","Case Study","","",""],["2021/01/07","2","4","3","林郁修","Term-project report","","Oral",""],["2021/01/14","2","4","3","林郁修","Term-project report","","Oral","Term-project report (Word) Due"]]}