機器學習與金融科技
Machine Learning and FinTech
| 節 | 週五 |
|---|---|
2 09:00–09:50 | 機器學習與金融科技 M102 3 節連堂 |
3 10:10–11:00 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
This course aims at training students with machine learning techniques. We introduce machine learning in statistical learning perspecitives, i.e., we formulate each machine learning technique as a constrained optimisation. Thus, how to reformulate a real-world problem is also a theme in this course. We will cover clustering, dimension reduction, classification, regression, and neural network. Specifically, each student will have to conduct a term projet in FinTech (individually or as a team of maximum of three members). Data analysis will be implemented in Python. In addition, two guest lectures in deep learning by Prof. Henry Horng-Shing Lu and high performance computing by Prof. Fang-Pang Lin will be delivered.
The prerequisites for this course are the undergraduate courses in statistics and calculus. Linear algebrea is beneficial but not required.
TA: To be announced
1. Participation (5%) 2. Homework (25%) : Homework will be assigned mostly weekly base. No late homework will be accepted. TA will post homework solutions for reference in new E3. 3. One exam (35%): In class and open-book 4. Project (35%)
| 週次 | 主題 |
|---|---|
| 第 1 週 | Syllabus, overview |
| 第 2 週 | EDA |
| 第 3 週 | unsupervised learning, K-means clustering |
| 第 4 週 | hier-archical clustering, PCA, crypto returns |
| 第 5 週 | c1: introduction, c2: statistical learning, c3: regression |
| 第 6 週 | c3: regression |
| 第 7 週 | c4: logistic regression |
| 第 8 週 | c4: LDA, QDA, Naive Bayes |
| 第 9 週 | c5: resampling, c6: model selection |
| 第 10 週 | Additional Topic: Neural networks |
| 第 11 週 | Additional Topic: Text mining |
| 第 12 週 | Exam |
| 第 13 週 | High-performance computing and blockchain. By Prof. Fang-Pang Lin. |
| 第 14 週 | Deep learning by Prof. Hong-Hsin Lu |
| 第 15 週 | Presentation |
| 第 16 週 | Presentation |
| 第 17 週 | Break (New Year) |
| 第 18 週 | Discussions (by appointment) |
The following reference textbooks can be freely download from the NYCU library: Required: James, Witten, Hastie, Tibshirani (2013) An Introduction to Statistical Learning with applications in R. Springer. Reference: Hastie, Tibshirani, and Freidman (2009) The Elements of Statistical Learning. Springer
- 地點
- online meeting through Microsoft Teams
- 時間
- by appointment
- 聯絡方式
- Email: venteng@gmail.com