Type of Credit: Elective
Credit(s)
Number of Students
In the course, we will extensively teach statistical analysis methods and machine learning techniques. A systematic explanation will be provided for various methods, addressing the characteristics of different data types and analysis approaches. The content includes linear models, non-linear models, techniques for classification problems, neural networks, deep learning, and text mining.
能力項目說明
Students enrolled in the course are expected to acquire a preliminary understanding of various statistical analysis methods and machine learning techniques. They will delve into the underlying mathematical logic and apply numerous methods in practical scenarios using programming languages such as R or Python. The goal is to empower students to comprehend how to choose appropriate analytical tools for data analysis in different contexts. Furthermore, they will develop the ability to interpret and discuss analysis results, laying the groundwork for foundational skills as aspiring data analysts.
| 教學週次Course Week | 彈性補充教學週次Flexible Supplemental Instruction Week | 彈性補充教學類別Flexible Supplemental Instruction Type |
|---|---|---|
|
Week |
Topic |
Content and Reading Assignment |
Teaching Activities and Homework |
|
1 |
Perceptron Learning Algorithm (PLA) |
Perceptron Learning Algorithm (PLA) |
PowerPoint and assign homework assignment for practicing PLA method in R or Python |
|
2 |
Learning Types and Error Measures |
Supervised or Unsupervised Learning and Weighted losses |
PowerPoint and homework assignment for finding several learning algorithms that belong to which type of learning techniques |
|
3 |
Regression Models |
Linear Regression Models and Logistic Regression Models |
PowerPoint and homework assignment for practicing linear methods in R or Python |
|
4 |
Support Vector Machine (SVM) |
Hard SVM and Dual SVM |
PowerPoint and homework assignment for practicing SVM in R or Python |
|
5 |
Support Vector Machine (SVM) |
Soft SVM and Kernel SVM |
PowerPoint and homework assignment for practicing kernel SVM in R or Python |
|
6 |
Lasso |
Lasso for high-dimensional regression Models |
PowerPoint and homework assignment for practicing Lasso in R or Python |
|
7 |
Kernel Logistic Regression (KLR) and Support Vector Regression (SVR) |
KLR and SVR |
PowerPoint and homework assignment for practicing KLR and SVR in R or Python |
|
8 |
Midterm Exam |
Midterm Exam |
Midterm Exam |
|
9 |
Blending, Bagging and Boosting |
Blending, Bagging and Adaptive Boosting method |
PowerPoint and homework assignment for practicing AdaBoost in R or Python |
|
10 |
Random Forest |
Decision Tree and Random Forest |
PowerPoint and homework assignment for practicing Random Forest method in R or Python |
|
11 |
Random Forest |
Gradient Boosted Decision Tree (GBDT) |
PowerPoint and homework assignment for practicing GBDT in R or Python |
|
12 |
Neural Network |
Neural Network (NN) |
PowerPoint and homework assignment for practicing NN in R or Python |
|
13 |
Radial Basis Function (RBF) Network |
RBF Network and K-means algorithm |
PowerPoint and homework assignment for practicing RBF Network and K-means in R or Python |
|
14 |
Deep Learning |
Brief Introducing Deep Learning |
PowerPoint and homework assignment for practicing Deep Learning in R or Python |
|
15 |
Text Mining |
Brief Introducing Text Mining |
PowerPoint and homework assignment for practicing Text Mining in R or Python |
|
16 |
Final Exam |
Final Exam |
Final Exam |
1. Midterm Exam (40%)：Physical examination and paper-based assessments will cover the content from the first to the seventh week of the course.
2. Final Exam (40%)：Physical examination and paper-based assessments will cover the content from the ninth to the fifteenth week of the course.
3. Regular homework assignments (20%).
An Introduction to Statistical Learning with Applications in R. Second Edition. Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani.
Not Applicable