一、課程說明 (Course Desc<x>ription) 
<br>This course introduces students to the fundamentals, problem-solving methods, 
<br>knowledge and reasoning, and learning paradigms of artificial intelligence. 
<br>Topics covered include intelligent agents, uninformed and informed search, 
<br>genetic algorithm, games, knowledge ba<x>sed systems, propositional logic, machine 
<br>learning, and neural networks.
<br>
<br>Goals:
<br>1. Learn the fundamentals and technologies of AI 
<br>2. Learn to use AI approaches to solve practical and engineering problems 
<br>3. Establish the foundation for future use, study, and research of AI
<br>
<br><strong>Prerequisite: Computer Programming</strong>
<br>Must have reasonable programming ability (C, C++, Java, or Python) and knowledge 
<br>about data structures and algorithms.
<br><font color="red">*There will be an exam on programming ability, as well as 
<br>basics of data structures and algorithms, in the first class.</font>
<br>
<br>
<br>二、指定用書 (Text Books) 
<br>S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, Prentice 
<br>Hill
<br>
<br>
<br>三、參考書籍 (References)
<br>M. Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, Addison 
<br>Wesley
<br>H. Kleine B&#252;ning and T. Lettmann, Propositional Logic: Deduction and Algorithms, 
<br>Cambridge University Press
<br>A.E. Eiben and J.E. Smith, Introduction to Evolutionary Computing, Springer
<br>
<br>
<br>四、教學方式 (Teaching Method)
<br>Lecture slides and blackboard teaching
<br>
<br>
<br>五、教學進度 (Syllabus)
<br>1. Introduction
<br>2. Intelligent Agents
<br>3. Solving Problems by Searching
<br>4. Informed Search
<br>5. Genetic Algorithm
<br>6. Adversarial Search
<br>7. Knowledge-ba<x>sed Systems and Logical Agents
<br>8. Machine Learning
<br>9. Neural Networks
<br>
<br>
<br>六、成績考核 (Evaluation) 
<br>Midterm Exam: 30%
<br>Final Exam: 30%
<br>Assignments & Project: 40%
<br>
<br>
<br>七、可連結之網頁位址 (Website)
<br>All materials and information will be announced on eeClass.
<br>