開課班級Class: 授課教師Teacher: 學分數Credits:
四生機四A 張仲良 3
課程大綱Course Description:
本課程內容將著重於介紹各種軟計算的方法,包括遺傳學、進化論、粒子群、人類神經系統、模
糊計算以及深度學習等。最終修課學生能獲得各種軟計算的方法與學理並能透過數值模擬軟體或
是開源式的框架來建構簡單的計算方法並應用於特定產業的工程問題。
English Outline:
This course will focus on introducing various soft computing methods, including genetics, evolution
theory, particle swarms, human nervous system, fuzzy computing, and deep learning. At the end of the
course, students can understand various soft computing methods, theories and operations, and can use
numerical simulation software or Python-based open source frameworks to construct simple computing
methods and apply them to engineering problems in specific industries.
本科目教學目標Course Objectives:
1. 瞭解軟計算的理論基礎,包括各種類型的軟計算技術,以及軟計算的應用。
2. 瞭解各種軟計算方法的功能操作。
3. 能利用計算機模擬軟體來評估計算智慧技術並應用於特定工程問題。
教學型態Teaching Models: 成績考核方式Grading:
課堂教學  平時成績General Performance:15%
期中考Midterm Exam:20%
期末考Final exam:20%
其它 Other:出缺勤(10%)、課程作業(15%)、期末報告(20%)
參考書目Textbooks/References:
1. D. K. Pratihar, Soft Computing : Fundamentals and Applications (2nd Ed.), 2013 2. K. A.
De Jong, Evolutionary Computing : A Unified Approach, Prentice Hall, 2009 3. Simon Haykin, Neural
Networks and Learning Machines (3rd Edn.), 2011. 4. Timothy J. Ross , Fuzzy Logic with Engineering
Applications (3rd Edn.), John Wiley & Sons, Inc. (ISBN: 978-0-470-74376-8) 5. Melanie Mitchell, An
Introduction to Genetic Algorithms, MIT Press, 2000. 6. M. P. Deisenroth, A. A. Faisal, C. S. Ong,
Mathematics for Machine Learning, Cambridge University Press, 2020. 7. S. Rajasekaran, G. A.
Vijayalakshmi Pai (2003). Neural Networks, Fuzzy Logic and Genetic Algorithms: Synthesis and
Applications, Prentice-Hall. (ISBN 0-471-70789-9)
SDGs指標:
UCAN職業項目:
工程及技術(生物機電)人才,製程研發(生物機電)人才
課程更新狀態:
課程匯入時間Import Time:2023-02-01 09:40:56
最後更新時間Last Modified:2023-02-08 13:36:46,更新人modified by:張仲良