一、課程說明(Course Desc<x>ription)
<br>
<br>To investigate and discuss the newly developed methodologies both in theory 
<br>and on algorithm so that the uncertainty caused by complex or large-scaled 
<br>problems can be analyzed and solved. 
<br>
<br> 二、指定用書(Text Books)
<br>
<br>Class Handout, WEKA 3-5-5 Explorer
<br>
<br>
<br> 三、參考書籍(References)
<br>
<br>papers
<br>
<br> 四、教學方式(Teaching Method)
<br>
<br>This is designed in particular for the Ph.D. students so that through paper 
<br>reading, discussion and brain storming, the students can have deeper and 
<br>wider insights towards OR development. Proposal of new ideas are thus highly 
<br>encouraged. Different subjects will be introduced by different lecturers. 
<br>
<br> 五、教學進度(Syllabus)
<br>
<br>第1週.   2/26. 課程規則與基本介紹
<br>第2週.   3/5.  柔性演算介紹
<br>第3週.   3/12. 簡化群體演算法應用（ㄧ）
<br>第4週.   3/19  簡化群體演算法應用（二）
<br>第5週.   3/26  SSO於可靠度工程之應用
<br>第6週.   4/2.  基因演算法 (GA)
<br>第7週.   4/9.  粒子群集最佳化演算法（PSO）
<br>第8週.   4/16  Midterm Exam
<br>第9週.   4/23. 人工蜂群演算法 (ABC)
<br>第10週.  4/30  BAT 演算法
<br>第11週.  5/7   機器學習(Machine Learning) – 類神經網絡 (ANN)
<br>第12週.  5/14  深度學習與最佳化方法（Deep Learning & Optimization）
<br>第13週.  5/21  SSO於神經網路之應用
<br>第14週.  5/28. 深度學習(Deep Learning) – CNN
<br>第15週.  6/4   深度學習(Deep Learning) – RNN & LSTM
<br>第16週.  6/11  強化學習（GAN）
<br>第17週.  6/18  實作演練
<br>第18週.  6/25  期末專題報告
<br>
<br>實驗數據分析
<br>
<br>
<br> 六、成績考核(Evaluation)
<br>
<br>Oral and Paper presentation
<br>
<br> 七、可連結之網頁位址
<br>
<br>https://sites.google.com/site/integrationcollaborationlab/
<br>