一、課程說明(Course Desc<x>ription) 
<br>This course introduces basic concepts in machine learning and their associated 
<br>mathematical tools. It is aimed at advanced undergraduates, and assumes no 
<br>previous knowledge of or machine learning concepts. Knowledge of multivariate 
<br>calculus, basic linear algebra some familiarity with probabilities would be 
<br>helpful but not essential. Topics to be covered include probability 
<br>distributions, supervised learning, Bayesian decision theory, parametric 
<br>methods, multivariate methods, dimensionality reduction, clustering, 
<br>nonparametric methods, decision trees, linear discrimination, multil<x>ayer 
<br>perceptrons, and deep learning. 
<br>
<br>二、指定用書(Text Books)
<br>Introduction to Machine Learning, Ethem Alpaydin, 3rd ed. 2014, The MIT Press.
<br>
<br>三、參考書籍(References) 
<br>1. Applied Statistics and Probability for Engineers, Douglas C. 
<br>Montgomery, 6th ed. 2014, John Wiley & Sons.
<br>
<br>四、教學方式(Teaching Method) 
<br>課堂授課，每周上課 150 分鐘
<br>
<br>五、教學進度 (Syllabus)
<br>1. Introduction 
<br>2. Math Background
<br>3. Supervised Learning 
<br>4. Bayesian Decision Theory 
<br>5. Parametric Methods 
<br>6. Multivariate Methods 
<br>7. Dimensionality Reduction 
<br>8. Clustering 
<br>9. Nonparametric Methods 
<br>10. Linear Discrimination 
<br>11. Multil<x>ayer Perceptron 
<br>12. Deep Learning
<br>
<br>六、成績考核(Evaluation) 
<br>1. Computer Assignments 40%
<br>2. Personal Project (Oral Presentation + Report) 35%
<br>3. Class Competition (Competition ranking) 25%
<br>
<br>No make-up exam!!
<br>
<br>Student use of the AI: Conditionally open; please specify how generative AI will 
<br>be used in course output.
<br>